diff --git a/test/test_download.py b/test/test_download.py index d1d6b119b..b3fd7d992 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -13,186 +13,186 @@ from youtube_dl.InfoExtractors import CollegeHumorIE, XNXXIE class DownloadTest(unittest.TestCase): - PARAMETERS_FILE = "test/parameters.json" - #calculated with md5sum: - #md5sum (GNU coreutils) 8.19 - - YOUTUBE_SIZE = 1993883 - YOUTUBE_URL = "http://www.youtube.com/watch?v=BaW_jenozKc" - YOUTUBE_FILE = "BaW_jenozKc.mp4" - - DAILYMOTION_MD5 = "d363a50e9eb4f22ce90d08d15695bb47" - DAILYMOTION_URL = "http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech" - DAILYMOTION_FILE = "x33vw9.mp4" - - METACAFE_SIZE = 5754305 - METACAFE_URL = "http://www.metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/" - METACAFE_FILE = "_aUehQsCQtM.flv" - - BLIP_MD5 = "93c24d2f4e0782af13b8a7606ea97ba7" - BLIP_URL = "http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352" - BLIP_FILE = "5779306.m4v" - - XVIDEO_MD5 = "1ab4dedc01f771cb2a65e91caa801aaf" - XVIDEO_URL = "http://www.xvideos.com/video939581/funny_porns_by_s_-1" - XVIDEO_FILE = "939581.flv" - - VIMEO_MD5 = "1ab4dedc01f771cb2a65e91caa801aaf" - VIMEO_URL = "http://vimeo.com/14160053" - VIMEO_FILE = "" - - VIMEO2_MD5 = "" - VIMEO2_URL = "http://player.vimeo.com/video/47019590" - VIMEO2_FILE = "" - - SOUNDCLOUD_MD5 = "ce3775768ebb6432fa8495d446a078ed" - SOUNDCLOUD_URL = "http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy" - SOUNDCLOUD_FILE = "n6FLbx6ZzMiu.mp3" - - STANDFORD_MD5 = "22c8206291368c4e2c9c1a307f0ea0f4" - STANDFORD_URL = "http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100" - STANDFORD_FILE = "PracticalUnix_intro-environment.mp4" - - COLLEGEHUMOR_MD5 = "" - COLLEGEHUMOR_URL = "http://www.collegehumor.com/video/6830834/mitt-romney-style-gangnam-style-parody" - COLLEGEHUMOR_FILE = "" - - XNXX_MD5 = "5f0469c8d1dfd1bc38c8e6deb5e0a21d" - XNXX_URL = "http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_" - XNXX_FILE = "1135332.flv" - - def test_youtube(self): - #let's download a file from youtube - with open(DownloadTest.PARAMETERS_FILE) as f: - fd = FileDownloader(json.load(f)) - fd.add_info_extractor(YoutubeIE()) - fd.download([DownloadTest.YOUTUBE_URL]) - self.assertTrue(os.path.exists(DownloadTest.YOUTUBE_FILE)) - self.assertEqual(os.path.getsize(DownloadTest.YOUTUBE_FILE), DownloadTest.YOUTUBE_SIZE) - - def test_dailymotion(self): - with open(DownloadTest.PARAMETERS_FILE) as f: - fd = FileDownloader(json.load(f)) - fd.add_info_extractor(DailymotionIE()) - fd.download([DownloadTest.DAILYMOTION_URL]) - self.assertTrue(os.path.exists(DownloadTest.DAILYMOTION_FILE)) - md5_down_file = md5_for_file(DownloadTest.DAILYMOTION_FILE) - self.assertEqual(md5_down_file, DownloadTest.DAILYMOTION_MD5) - - def test_metacafe(self): - #this emulate a skip,to be 2.6 compatible - with open(DownloadTest.PARAMETERS_FILE) as f: - fd = FileDownloader(json.load(f)) - fd.add_info_extractor(MetacafeIE()) - fd.add_info_extractor(YoutubeIE()) - fd.download([DownloadTest.METACAFE_URL]) - self.assertTrue(os.path.exists(DownloadTest.METACAFE_FILE)) - self.assertEqual(os.path.getsize(DownloadTest.METACAFE_FILE), DownloadTest.METACAFE_SIZE) - - def test_blip(self): - with open(DownloadTest.PARAMETERS_FILE) as f: - fd = FileDownloader(json.load(f)) - fd.add_info_extractor(BlipTVIE()) - fd.download([DownloadTest.BLIP_URL]) - self.assertTrue(os.path.exists(DownloadTest.BLIP_FILE)) - md5_down_file = md5_for_file(DownloadTest.BLIP_FILE) - self.assertEqual(md5_down_file, DownloadTest.BLIP_MD5) - - def test_xvideo(self): - with open(DownloadTest.PARAMETERS_FILE) as f: - fd = FileDownloader(json.load(f)) - fd.add_info_extractor(XVideosIE()) - fd.download([DownloadTest.XVIDEO_URL]) - self.assertTrue(os.path.exists(DownloadTest.XVIDEO_FILE)) - md5_down_file = md5_for_file(DownloadTest.XVIDEO_FILE) - self.assertEqual(md5_down_file, DownloadTest.XVIDEO_MD5) - - def test_vimeo(self): - #skipped for the moment produce an error - return - with open(DownloadTest.PARAMETERS_FILE) as f: - fd = FileDownloader(json.load(f)) - fd.add_info_extractor(VimeoIE()) - fd.download([DownloadTest.VIMEO_URL]) - self.assertTrue(os.path.exists(DownloadTest.VIMEO_FILE)) - md5_down_file = md5_for_file(DownloadTest.VIMEO_FILE) - self.assertEqual(md5_down_file, DownloadTest.VIMEO_MD5) - - def test_vimeo2(self): - #skipped for the moment produce an error - return - with open(DownloadTest.PARAMETERS_FILE) as f: - fd = FileDownloader(json.load(f)) - fd.add_info_extractor(VimeoIE()) - fd.download([DownloadTest.VIMEO2_URL]) - self.assertTrue(os.path.exists(DownloadTest.VIMEO2_FILE)) - md5_down_file = md5_for_file(DownloadTest.VIMEO2_FILE) - self.assertEqual(md5_down_file, DownloadTest.VIMEO2_MD5) - - def test_soundcloud(self): - with open(DownloadTest.PARAMETERS_FILE) as f: - fd = FileDownloader(json.load(f)) - fd.add_info_extractor(SoundcloudIE()) - fd.download([DownloadTest.SOUNDCLOUD_URL]) - self.assertTrue(os.path.exists(DownloadTest.SOUNDCLOUD_FILE)) - md5_down_file = md5_for_file(DownloadTest.SOUNDCLOUD_FILE) - self.assertEqual(md5_down_file, DownloadTest.SOUNDCLOUD_MD5) - - def test_standford(self): - with open(DownloadTest.PARAMETERS_FILE) as f: - fd = FileDownloader(json.load(f)) - fd.add_info_extractor(StanfordOpenClassroomIE()) - fd.download([DownloadTest.STANDFORD_URL]) - self.assertTrue(os.path.exists(DownloadTest.STANDFORD_FILE)) - md5_down_file = md5_for_file(DownloadTest.STANDFORD_FILE) - self.assertEqual(md5_down_file, DownloadTest.STANDFORD_MD5) - - def test_collegehumor(self): - with open(DownloadTest.PARAMETERS_FILE) as f: - fd = FileDownloader(json.load(f)) - fd.add_info_extractor(CollegeHumorIE()) - fd.download([DownloadTest.COLLEGEHUMOR_URL]) - self.assertTrue(os.path.exists(DownloadTest.COLLEGEHUMOR_FILE)) - md5_down_file = md5_for_file(DownloadTest.COLLEGEHUMOR_FILE) - self.assertEqual(md5_down_file, DownloadTest.COLLEGEHUMOR_MD5) - - def test_xnxx(self): - with open(DownloadTest.PARAMETERS_FILE) as f: - fd = FileDownloader(json.load(f)) - fd.add_info_extractor(XNXXIE()) - fd.download([DownloadTest.XNXX_URL]) - self.assertTrue(os.path.exists(DownloadTest.XNXX_FILE)) - md5_down_file = md5_for_file(DownloadTest.XNXX_FILE) - self.assertEqual(md5_down_file, DownloadTest.XNXX_MD5) - - def tearDown(self): - if os.path.exists(DownloadTest.YOUTUBE_FILE): - os.remove(DownloadTest.YOUTUBE_FILE) - if os.path.exists(DownloadTest.DAILYMOTION_FILE): - os.remove(DownloadTest.DAILYMOTION_FILE) - if os.path.exists(DownloadTest.METACAFE_FILE): - os.remove(DownloadTest.METACAFE_FILE) - if os.path.exists(DownloadTest.BLIP_FILE): - os.remove(DownloadTest.BLIP_FILE) - if os.path.exists(DownloadTest.XVIDEO_FILE): - os.remove(DownloadTest.XVIDEO_FILE) - if os.path.exists(DownloadTest.VIMEO_FILE): - os.remove(DownloadTest.VIMEO_FILE) - if os.path.exists(DownloadTest.SOUNDCLOUD_FILE): - os.remove(DownloadTest.SOUNDCLOUD_FILE) - if os.path.exists(DownloadTest.STANDFORD_FILE): - os.remove(DownloadTest.STANDFORD_FILE) - if os.path.exists(DownloadTest.COLLEGEHUMOR_FILE): - os.remove(DownloadTest.COLLEGEHUMOR_FILE) - if os.path.exists(DownloadTest.XNXX_FILE): - os.remove(DownloadTest.XNXX_FILE) + PARAMETERS_FILE = "test/parameters.json" + #calculated with md5sum: + #md5sum (GNU coreutils) 8.19 + + YOUTUBE_SIZE = 1993883 + YOUTUBE_URL = "http://www.youtube.com/watch?v=BaW_jenozKc" + YOUTUBE_FILE = "BaW_jenozKc.mp4" + + DAILYMOTION_MD5 = "d363a50e9eb4f22ce90d08d15695bb47" + DAILYMOTION_URL = "http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech" + DAILYMOTION_FILE = "x33vw9.mp4" + + METACAFE_SIZE = 5754305 + METACAFE_URL = "http://www.metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/" + METACAFE_FILE = "_aUehQsCQtM.flv" + + BLIP_MD5 = "93c24d2f4e0782af13b8a7606ea97ba7" + BLIP_URL = "http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352" + BLIP_FILE = "5779306.m4v" + + XVIDEO_MD5 = "1ab4dedc01f771cb2a65e91caa801aaf" + XVIDEO_URL = "http://www.xvideos.com/video939581/funny_porns_by_s_-1" + XVIDEO_FILE = "939581.flv" + + VIMEO_MD5 = "1ab4dedc01f771cb2a65e91caa801aaf" + VIMEO_URL = "http://vimeo.com/14160053" + VIMEO_FILE = "" + + VIMEO2_MD5 = "" + VIMEO2_URL = "http://player.vimeo.com/video/47019590" + VIMEO2_FILE = "" + + SOUNDCLOUD_MD5 = "ce3775768ebb6432fa8495d446a078ed" + SOUNDCLOUD_URL = "http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy" + SOUNDCLOUD_FILE = "n6FLbx6ZzMiu.mp3" + + STANDFORD_MD5 = "22c8206291368c4e2c9c1a307f0ea0f4" + STANDFORD_URL = "http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100" + STANDFORD_FILE = "PracticalUnix_intro-environment.mp4" + + COLLEGEHUMOR_MD5 = "" + COLLEGEHUMOR_URL = "http://www.collegehumor.com/video/6830834/mitt-romney-style-gangnam-style-parody" + COLLEGEHUMOR_FILE = "" + + XNXX_MD5 = "5f0469c8d1dfd1bc38c8e6deb5e0a21d" + XNXX_URL = "http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_" + XNXX_FILE = "1135332.flv" + + def test_youtube(self): + #let's download a file from youtube + with open(DownloadTest.PARAMETERS_FILE) as f: + fd = FileDownloader(json.load(f)) + fd.add_info_extractor(YoutubeIE()) + fd.download([DownloadTest.YOUTUBE_URL]) + self.assertTrue(os.path.exists(DownloadTest.YOUTUBE_FILE)) + self.assertEqual(os.path.getsize(DownloadTest.YOUTUBE_FILE), DownloadTest.YOUTUBE_SIZE) + + def test_dailymotion(self): + with open(DownloadTest.PARAMETERS_FILE) as f: + fd = FileDownloader(json.load(f)) + fd.add_info_extractor(DailymotionIE()) + fd.download([DownloadTest.DAILYMOTION_URL]) + self.assertTrue(os.path.exists(DownloadTest.DAILYMOTION_FILE)) + md5_down_file = md5_for_file(DownloadTest.DAILYMOTION_FILE) + self.assertEqual(md5_down_file, DownloadTest.DAILYMOTION_MD5) + + def test_metacafe(self): + #this emulate a skip,to be 2.6 compatible + with open(DownloadTest.PARAMETERS_FILE) as f: + fd = FileDownloader(json.load(f)) + fd.add_info_extractor(MetacafeIE()) + fd.add_info_extractor(YoutubeIE()) + fd.download([DownloadTest.METACAFE_URL]) + self.assertTrue(os.path.exists(DownloadTest.METACAFE_FILE)) + self.assertEqual(os.path.getsize(DownloadTest.METACAFE_FILE), DownloadTest.METACAFE_SIZE) + + def test_blip(self): + with open(DownloadTest.PARAMETERS_FILE) as f: + fd = FileDownloader(json.load(f)) + fd.add_info_extractor(BlipTVIE()) + fd.download([DownloadTest.BLIP_URL]) + self.assertTrue(os.path.exists(DownloadTest.BLIP_FILE)) + md5_down_file = md5_for_file(DownloadTest.BLIP_FILE) + self.assertEqual(md5_down_file, DownloadTest.BLIP_MD5) + + def test_xvideo(self): + with open(DownloadTest.PARAMETERS_FILE) as f: + fd = FileDownloader(json.load(f)) + fd.add_info_extractor(XVideosIE()) + fd.download([DownloadTest.XVIDEO_URL]) + self.assertTrue(os.path.exists(DownloadTest.XVIDEO_FILE)) + md5_down_file = md5_for_file(DownloadTest.XVIDEO_FILE) + self.assertEqual(md5_down_file, DownloadTest.XVIDEO_MD5) + + def test_vimeo(self): + #skipped for the moment produce an error + return + with open(DownloadTest.PARAMETERS_FILE) as f: + fd = FileDownloader(json.load(f)) + fd.add_info_extractor(VimeoIE()) + fd.download([DownloadTest.VIMEO_URL]) + self.assertTrue(os.path.exists(DownloadTest.VIMEO_FILE)) + md5_down_file = md5_for_file(DownloadTest.VIMEO_FILE) + self.assertEqual(md5_down_file, DownloadTest.VIMEO_MD5) + + def test_vimeo2(self): + #skipped for the moment produce an error + return + with open(DownloadTest.PARAMETERS_FILE) as f: + fd = FileDownloader(json.load(f)) + fd.add_info_extractor(VimeoIE()) + fd.download([DownloadTest.VIMEO2_URL]) + self.assertTrue(os.path.exists(DownloadTest.VIMEO2_FILE)) + md5_down_file = md5_for_file(DownloadTest.VIMEO2_FILE) + self.assertEqual(md5_down_file, DownloadTest.VIMEO2_MD5) + + def test_soundcloud(self): + with open(DownloadTest.PARAMETERS_FILE) as f: + fd = FileDownloader(json.load(f)) + fd.add_info_extractor(SoundcloudIE()) + fd.download([DownloadTest.SOUNDCLOUD_URL]) + self.assertTrue(os.path.exists(DownloadTest.SOUNDCLOUD_FILE)) + md5_down_file = md5_for_file(DownloadTest.SOUNDCLOUD_FILE) + self.assertEqual(md5_down_file, DownloadTest.SOUNDCLOUD_MD5) + + def test_standford(self): + with open(DownloadTest.PARAMETERS_FILE) as f: + fd = FileDownloader(json.load(f)) + fd.add_info_extractor(StanfordOpenClassroomIE()) + fd.download([DownloadTest.STANDFORD_URL]) + self.assertTrue(os.path.exists(DownloadTest.STANDFORD_FILE)) + md5_down_file = md5_for_file(DownloadTest.STANDFORD_FILE) + self.assertEqual(md5_down_file, DownloadTest.STANDFORD_MD5) + + def test_collegehumor(self): + with open(DownloadTest.PARAMETERS_FILE) as f: + fd = FileDownloader(json.load(f)) + fd.add_info_extractor(CollegeHumorIE()) + fd.download([DownloadTest.COLLEGEHUMOR_URL]) + self.assertTrue(os.path.exists(DownloadTest.COLLEGEHUMOR_FILE)) + md5_down_file = md5_for_file(DownloadTest.COLLEGEHUMOR_FILE) + self.assertEqual(md5_down_file, DownloadTest.COLLEGEHUMOR_MD5) + + def test_xnxx(self): + with open(DownloadTest.PARAMETERS_FILE) as f: + fd = FileDownloader(json.load(f)) + fd.add_info_extractor(XNXXIE()) + fd.download([DownloadTest.XNXX_URL]) + self.assertTrue(os.path.exists(DownloadTest.XNXX_FILE)) + md5_down_file = md5_for_file(DownloadTest.XNXX_FILE) + self.assertEqual(md5_down_file, DownloadTest.XNXX_MD5) + + def tearDown(self): + if os.path.exists(DownloadTest.YOUTUBE_FILE): + os.remove(DownloadTest.YOUTUBE_FILE) + if os.path.exists(DownloadTest.DAILYMOTION_FILE): + os.remove(DownloadTest.DAILYMOTION_FILE) + if os.path.exists(DownloadTest.METACAFE_FILE): + os.remove(DownloadTest.METACAFE_FILE) + if os.path.exists(DownloadTest.BLIP_FILE): + os.remove(DownloadTest.BLIP_FILE) + if os.path.exists(DownloadTest.XVIDEO_FILE): + os.remove(DownloadTest.XVIDEO_FILE) + if os.path.exists(DownloadTest.VIMEO_FILE): + os.remove(DownloadTest.VIMEO_FILE) + if os.path.exists(DownloadTest.SOUNDCLOUD_FILE): + os.remove(DownloadTest.SOUNDCLOUD_FILE) + if os.path.exists(DownloadTest.STANDFORD_FILE): + os.remove(DownloadTest.STANDFORD_FILE) + if os.path.exists(DownloadTest.COLLEGEHUMOR_FILE): + os.remove(DownloadTest.COLLEGEHUMOR_FILE) + if os.path.exists(DownloadTest.XNXX_FILE): + os.remove(DownloadTest.XNXX_FILE) def md5_for_file(filename, block_size=2**20): - with open(filename) as f: - md5 = hashlib.md5() - while True: - data = f.read(block_size) - if not data: - break - md5.update(data) - return md5.hexdigest() + with open(filename) as f: + md5 = hashlib.md5() + while True: + data = f.read(block_size) + if not data: + break + md5.update(data) + return md5.hexdigest() diff --git a/test/test_import.py b/test/test_import.py index 6c5d0bcc1..acf95444d 100644 --- a/test/test_import.py +++ b/test/test_import.py @@ -5,9 +5,9 @@ import os.path import subprocess class TestImport(unittest.TestCase): - def test_import(self): - rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) - subprocess.check_call([sys.executable, '-c', 'import youtube_dl'], cwd=rootDir) + def test_import(self): + rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) + subprocess.check_call([sys.executable, '-c', 'import youtube_dl'], cwd=rootDir) if __name__ == '__main__': - unittest.main() + unittest.main() diff --git a/test/test_utils.py b/test/test_utils.py index e2f226bf1..ceefabefc 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -14,79 +14,79 @@ from youtube_dl.utils import unescapeHTML from youtube_dl.utils import orderedSet if sys.version_info < (3,0): - _compat_str = lambda b: b.decode('unicode-escape') + _compat_str = lambda b: b.decode('unicode-escape') else: - _compat_str = lambda s: s + _compat_str = lambda s: s class TestUtil(unittest.TestCase): - def test_timeconvert(self): - self.assertTrue(timeconvert('') is None) - self.assertTrue(timeconvert('bougrg') is None) - - def test_sanitize_filename(self): - self.assertEqual(sanitize_filename('abc'), 'abc') - self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e') - - self.assertEqual(sanitize_filename('123'), '123') - - self.assertEqual('abc_de', sanitize_filename('abc/de')) - self.assertFalse('/' in sanitize_filename('abc/de///')) - - self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de')) - self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|')) - self.assertEqual('yes no', sanitize_filename('yes? no')) - self.assertEqual('this - that', sanitize_filename('this: that')) - - self.assertEqual(sanitize_filename('AT&T'), 'AT&T') - aumlaut = _compat_str('\xe4') - self.assertEqual(sanitize_filename(aumlaut), aumlaut) - tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430') - self.assertEqual(sanitize_filename(tests), tests) - - forbidden = '"\0\\/' - for fc in forbidden: - for fbc in forbidden: - self.assertTrue(fbc not in sanitize_filename(fc)) - - def test_sanitize_filename_restricted(self): - self.assertEqual(sanitize_filename('abc', restricted=True), 'abc') - self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e') - - self.assertEqual(sanitize_filename('123', restricted=True), '123') - - self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True)) - self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True)) - - self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True)) - self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True)) - self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True)) - self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True)) - - tests =_compat_str('a\xe4b\u4e2d\u56fd\u7684c') - self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c') - self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename - - forbidden = '"\0\\/&!: \'\t\n' - for fc in forbidden: - for fbc in forbidden: - self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) - - # Handle a common case more neatly - self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song') - self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech') - # .. but make sure the file name is never empty - self.assertTrue(sanitize_filename('-', restricted=True) != '') - self.assertTrue(sanitize_filename(':', restricted=True) != '') - - def test_ordered_set(self): - self.assertEqual(orderedSet([1,1,2,3,4,4,5,6,7,3,5]), [1,2,3,4,5,6,7]) - self.assertEqual(orderedSet([]), []) - self.assertEqual(orderedSet([1]), [1]) - #keep the list ordered - self.assertEqual(orderedSet([135,1,1,1]), [135,1]) - - def test_unescape_html(self): - self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;')) + def test_timeconvert(self): + self.assertTrue(timeconvert('') is None) + self.assertTrue(timeconvert('bougrg') is None) + + def test_sanitize_filename(self): + self.assertEqual(sanitize_filename('abc'), 'abc') + self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e') + + self.assertEqual(sanitize_filename('123'), '123') + + self.assertEqual('abc_de', sanitize_filename('abc/de')) + self.assertFalse('/' in sanitize_filename('abc/de///')) + + self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de')) + self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|')) + self.assertEqual('yes no', sanitize_filename('yes? no')) + self.assertEqual('this - that', sanitize_filename('this: that')) + + self.assertEqual(sanitize_filename('AT&T'), 'AT&T') + aumlaut = _compat_str('\xe4') + self.assertEqual(sanitize_filename(aumlaut), aumlaut) + tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430') + self.assertEqual(sanitize_filename(tests), tests) + + forbidden = '"\0\\/' + for fc in forbidden: + for fbc in forbidden: + self.assertTrue(fbc not in sanitize_filename(fc)) + + def test_sanitize_filename_restricted(self): + self.assertEqual(sanitize_filename('abc', restricted=True), 'abc') + self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e') + + self.assertEqual(sanitize_filename('123', restricted=True), '123') + + self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True)) + self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True)) + + self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True)) + self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True)) + self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True)) + self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True)) + + tests =_compat_str('a\xe4b\u4e2d\u56fd\u7684c') + self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c') + self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename + + forbidden = '"\0\\/&!: \'\t\n' + for fc in forbidden: + for fbc in forbidden: + self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) + + # Handle a common case more neatly + self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song') + self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech') + # .. but make sure the file name is never empty + self.assertTrue(sanitize_filename('-', restricted=True) != '') + self.assertTrue(sanitize_filename(':', restricted=True) != '') + + def test_ordered_set(self): + self.assertEqual(orderedSet([1,1,2,3,4,4,5,6,7,3,5]), [1,2,3,4,5,6,7]) + self.assertEqual(orderedSet([]), []) + self.assertEqual(orderedSet([1]), [1]) + #keep the list ordered + self.assertEqual(orderedSet([135,1,1,1]), [135,1]) + + def test_unescape_html(self): + self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;')) if __name__ == '__main__': - unittest.main() + unittest.main() diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 9e9f2a0e4..9dc3523e0 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -10,707 +10,707 @@ import sys import time if os.name == 'nt': - import ctypes + import ctypes from utils import * class FileDownloader(object): - """File Downloader class. - - File downloader objects are the ones responsible of downloading the - actual video file and writing it to disk if the user has requested - it, among some other tasks. In most cases there should be one per - program. As, given a video URL, the downloader doesn't know how to - extract all the needed information, task that InfoExtractors do, it - has to pass the URL to one of them. - - For this, file downloader objects have a method that allows - InfoExtractors to be registered in a given order. When it is passed - a URL, the file downloader handles it to the first InfoExtractor it - finds that reports being able to handle it. The InfoExtractor extracts - all the information about the video or videos the URL refers to, and - asks the FileDownloader to process the video information, possibly - downloading the video. - - File downloaders accept a lot of parameters. In order not to saturate - the object constructor with arguments, it receives a dictionary of - options instead. These options are available through the params - attribute for the InfoExtractors to use. The FileDownloader also - registers itself as the downloader in charge for the InfoExtractors - that are added to it, so this is a "mutual registration". - - Available options: - - username: Username for authentication purposes. - password: Password for authentication purposes. - usenetrc: Use netrc for authentication instead. - quiet: Do not print messages to stdout. - forceurl: Force printing final URL. - forcetitle: Force printing title. - forcethumbnail: Force printing thumbnail URL. - forcedescription: Force printing description. - forcefilename: Force printing final filename. - simulate: Do not download the video files. - format: Video format code. - format_limit: Highest quality format to try. - outtmpl: Template for output names. - restrictfilenames: Do not allow "&" and spaces in file names - ignoreerrors: Do not stop on download errors. - ratelimit: Download speed limit, in bytes/sec. - nooverwrites: Prevent overwriting files. - retries: Number of times to retry for HTTP error 5xx - buffersize: Size of download buffer in bytes. - noresizebuffer: Do not automatically resize the download buffer. - continuedl: Try to continue downloads if possible. - noprogress: Do not print the progress bar. - playliststart: Playlist item to start at. - playlistend: Playlist item to end at. - matchtitle: Download only matching titles. - rejecttitle: Reject downloads for matching titles. - logtostderr: Log messages to stderr instead of stdout. - consoletitle: Display progress in console window's titlebar. - nopart: Do not use temporary .part files. - updatetime: Use the Last-modified header to set output file timestamps. - writedescription: Write the video description to a .description file - writeinfojson: Write the video description to a .info.json file - writesubtitles: Write the video subtitles to a .srt file - subtitleslang: Language of the subtitles to download - """ - - params = None - _ies = [] - _pps = [] - _download_retcode = None - _num_downloads = None - _screen_file = None - - def __init__(self, params): - """Create a FileDownloader object with the given options.""" - self._ies = [] - self._pps = [] - self._download_retcode = 0 - self._num_downloads = 0 - self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] - self.params = params - - if '%(stitle)s' in self.params['outtmpl']: - self.to_stderr(u'WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') - - @staticmethod - def format_bytes(bytes): - if bytes is None: - return 'N/A' - if type(bytes) is str: - bytes = float(bytes) - if bytes == 0.0: - exponent = 0 - else: - exponent = int(math.log(bytes, 1024.0)) - suffix = 'bkMGTPEZY'[exponent] - converted = float(bytes) / float(1024 ** exponent) - return '%.2f%s' % (converted, suffix) - - @staticmethod - def calc_percent(byte_counter, data_len): - if data_len is None: - return '---.-%' - return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) - - @staticmethod - def calc_eta(start, now, total, current): - if total is None: - return '--:--' - dif = now - start - if current == 0 or dif < 0.001: # One millisecond - return '--:--' - rate = float(current) / dif - eta = int((float(total) - float(current)) / rate) - (eta_mins, eta_secs) = divmod(eta, 60) - if eta_mins > 99: - return '--:--' - return '%02d:%02d' % (eta_mins, eta_secs) - - @staticmethod - def calc_speed(start, now, bytes): - dif = now - start - if bytes == 0 or dif < 0.001: # One millisecond - return '%10s' % '---b/s' - return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) - - @staticmethod - def best_block_size(elapsed_time, bytes): - new_min = max(bytes / 2.0, 1.0) - new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB - if elapsed_time < 0.001: - return int(new_max) - rate = bytes / elapsed_time - if rate > new_max: - return int(new_max) - if rate < new_min: - return int(new_min) - return int(rate) - - @staticmethod - def parse_bytes(bytestr): - """Parse a string indicating a byte quantity into an integer.""" - matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) - if matchobj is None: - return None - number = float(matchobj.group(1)) - multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) - return int(round(number * multiplier)) - - def add_info_extractor(self, ie): - """Add an InfoExtractor object to the end of the list.""" - self._ies.append(ie) - ie.set_downloader(self) - - def add_post_processor(self, pp): - """Add a PostProcessor object to the end of the chain.""" - self._pps.append(pp) - pp.set_downloader(self) - - def to_screen(self, message, skip_eol=False): - """Print message to stdout if not in quiet mode.""" - assert type(message) == type(u'') - if not self.params.get('quiet', False): - terminator = [u'\n', u''][skip_eol] - output = message + terminator - if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr - output = output.encode(preferredencoding(), 'ignore') - self._screen_file.write(output) - self._screen_file.flush() - - def to_stderr(self, message): - """Print message to stderr.""" - assert type(message) == type(u'') - output = message + u'\n' - if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr - output = output.encode(preferredencoding()) - sys.stderr.write(output) - - def to_cons_title(self, message): - """Set console/terminal window title to message.""" - if not self.params.get('consoletitle', False): - return - if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): - # c_wchar_p() might not be necessary if `message` is - # already of type unicode() - ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) - elif 'TERM' in os.environ: - sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding())) - - def fixed_template(self): - """Checks if the output template is fixed.""" - return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None) - - def trouble(self, message=None): - """Determine action to take when a download problem appears. - - Depending on if the downloader has been configured to ignore - download errors or not, this method may throw an exception or - not when errors are found, after printing the message. - """ - if message is not None: - self.to_stderr(message) - if not self.params.get('ignoreerrors', False): - raise DownloadError(message) - self._download_retcode = 1 - - def slow_down(self, start_time, byte_counter): - """Sleep if the download speed is over the rate limit.""" - rate_limit = self.params.get('ratelimit', None) - if rate_limit is None or byte_counter == 0: - return - now = time.time() - elapsed = now - start_time - if elapsed <= 0.0: - return - speed = float(byte_counter) / elapsed - if speed > rate_limit: - time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) - - def temp_name(self, filename): - """Returns a temporary filename for the given filename.""" - if self.params.get('nopart', False) or filename == u'-' or \ - (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))): - return filename - return filename + u'.part' - - def undo_temp_name(self, filename): - if filename.endswith(u'.part'): - return filename[:-len(u'.part')] - return filename - - def try_rename(self, old_filename, new_filename): - try: - if old_filename == new_filename: - return - os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) - except (IOError, OSError) as err: - self.trouble(u'ERROR: unable to rename file') - - def try_utime(self, filename, last_modified_hdr): - """Try to set the last-modified time of the given file.""" - if last_modified_hdr is None: - return - if not os.path.isfile(encodeFilename(filename)): - return - timestr = last_modified_hdr - if timestr is None: - return - filetime = timeconvert(timestr) - if filetime is None: - return filetime - try: - os.utime(filename, (time.time(), filetime)) - except: - pass - return filetime - - def report_writedescription(self, descfn): - """ Report that the description file is being written """ - self.to_screen(u'[info] Writing video description to: ' + descfn) - - def report_writesubtitles(self, srtfn): - """ Report that the subtitles file is being written """ - self.to_screen(u'[info] Writing video subtitles to: ' + srtfn) - - def report_writeinfojson(self, infofn): - """ Report that the metadata file has been written """ - self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) - - def report_destination(self, filename): - """Report destination filename.""" - self.to_screen(u'[download] Destination: ' + filename) - - def report_progress(self, percent_str, data_len_str, speed_str, eta_str): - """Report download progress.""" - if self.params.get('noprogress', False): - return - self.to_screen(u'\r[download] %s of %s at %s ETA %s' % - (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) - self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % - (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) - - def report_resuming_byte(self, resume_len): - """Report attempt to resume at given byte.""" - self.to_screen(u'[download] Resuming download at byte %s' % resume_len) - - def report_retry(self, count, retries): - """Report retry in case of HTTP error 5xx""" - self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) - - def report_file_already_downloaded(self, file_name): - """Report file has already been fully downloaded.""" - try: - self.to_screen(u'[download] %s has already been downloaded' % file_name) - except (UnicodeEncodeError) as err: - self.to_screen(u'[download] The file has already been downloaded') - - def report_unable_to_resume(self): - """Report it was impossible to resume download.""" - self.to_screen(u'[download] Unable to resume') - - def report_finish(self): - """Report download finished.""" - if self.params.get('noprogress', False): - self.to_screen(u'[download] Download completed') - else: - self.to_screen(u'') - - def increment_downloads(self): - """Increment the ordinal that assigns a number to each file.""" - self._num_downloads += 1 - - def prepare_filename(self, info_dict): - """Generate the output filename.""" - try: - template_dict = dict(info_dict) - - template_dict['epoch'] = int(time.time()) - template_dict['autonumber'] = u'%05d' % self._num_downloads - - template_dict = dict((key, u'NA' if val is None else val) for key, val in template_dict.items()) - template_dict = dict((k, sanitize_filename(compat_str(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) - - filename = self.params['outtmpl'] % template_dict - return filename - except (ValueError, KeyError) as err: - self.trouble(u'ERROR: invalid system charset or erroneous output template') - return None - - def _match_entry(self, info_dict): - """ Returns None iff the file should be downloaded """ - - title = info_dict['title'] - matchtitle = self.params.get('matchtitle', False) - if matchtitle: - matchtitle = matchtitle.decode('utf8') - if not re.search(matchtitle, title, re.IGNORECASE): - return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' - rejecttitle = self.params.get('rejecttitle', False) - if rejecttitle: - rejecttitle = rejecttitle.decode('utf8') - if re.search(rejecttitle, title, re.IGNORECASE): - return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' - return None - - def process_info(self, info_dict): - """Process a single dictionary returned by an InfoExtractor.""" - - # Keep for backwards compatibility - info_dict['stitle'] = info_dict['title'] - - if not 'format' in info_dict: - info_dict['format'] = info_dict['ext'] - - reason = self._match_entry(info_dict) - if reason is not None: - self.to_screen(u'[download] ' + reason) - return - - max_downloads = self.params.get('max_downloads') - if max_downloads is not None: - if self._num_downloads > int(max_downloads): - raise MaxDownloadsReached() - - filename = self.prepare_filename(info_dict) - - # Forced printings - if self.params.get('forcetitle', False): - compat_print(info_dict['title']) - if self.params.get('forceurl', False): - compat_print(info_dict['url']) - if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: - compat_print(info_dict['thumbnail']) - if self.params.get('forcedescription', False) and 'description' in info_dict: - compat_print(info_dict['description']) - if self.params.get('forcefilename', False) and filename is not None: - compat_print(filename) - if self.params.get('forceformat', False): - compat_print(info_dict['format']) - - # Do nothing else if in simulate mode - if self.params.get('simulate', False): - return - - if filename is None: - return - - try: - dn = os.path.dirname(encodeFilename(filename)) - if dn != '' and not os.path.exists(dn): # dn is already encoded - os.makedirs(dn) - except (OSError, IOError) as err: - self.trouble(u'ERROR: unable to create directory ' + compat_str(err)) - return - - if self.params.get('writedescription', False): - try: - descfn = filename + u'.description' - self.report_writedescription(descfn) - descfile = open(encodeFilename(descfn), 'wb') - try: - descfile.write(info_dict['description'].encode('utf-8')) - finally: - descfile.close() - except (OSError, IOError): - self.trouble(u'ERROR: Cannot write description file ' + descfn) - return - - if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: - # subtitles download errors are already managed as troubles in relevant IE - # that way it will silently go on when used with unsupporting IE - try: - srtfn = filename.rsplit('.', 1)[0] + u'.srt' - self.report_writesubtitles(srtfn) - srtfile = open(encodeFilename(srtfn), 'wb') - try: - srtfile.write(info_dict['subtitles'].encode('utf-8')) - finally: - srtfile.close() - except (OSError, IOError): - self.trouble(u'ERROR: Cannot write subtitles file ' + descfn) - return - - if self.params.get('writeinfojson', False): - infofn = filename + u'.info.json' - self.report_writeinfojson(infofn) - try: - json.dump - except (NameError,AttributeError): - self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') - return - try: - infof = open(encodeFilename(infofn), 'wb') - try: - json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',)) - json.dump(json_info_dict, infof) - finally: - infof.close() - except (OSError, IOError): - self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) - return - - if not self.params.get('skip_download', False): - if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): - success = True - else: - try: - success = self._do_download(filename, info_dict) - except (OSError, IOError) as err: - raise UnavailableVideoError - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self.trouble(u'ERROR: unable to download video data: %s' % str(err)) - return - except (ContentTooShortError, ) as err: - self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) - return - - if success: - try: - self.post_process(filename, info_dict) - except (PostProcessingError) as err: - self.trouble(u'ERROR: postprocessing: %s' % str(err)) - return - - def download(self, url_list): - """Download a given list of URLs.""" - if len(url_list) > 1 and self.fixed_template(): - raise SameFileError(self.params['outtmpl']) - - for url in url_list: - suitable_found = False - for ie in self._ies: - # Go to next InfoExtractor if not suitable - if not ie.suitable(url): - continue - - # Warn if the _WORKING attribute is False - if not ie.working(): - self.trouble(u'WARNING: the program functionality for this site has been marked as broken, ' - u'and will probably not work. If you want to go on, use the -i option.') - - # Suitable InfoExtractor found - suitable_found = True - - # Extract information from URL and process it - videos = ie.extract(url) - for video in videos or []: - video['extractor'] = ie.IE_NAME - try: - self.increment_downloads() - self.process_info(video) - except UnavailableVideoError: - self.trouble(u'\nERROR: unable to download video') - - # Suitable InfoExtractor had been found; go to next URL - break - - if not suitable_found: - self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) - - return self._download_retcode - - def post_process(self, filename, ie_info): - """Run the postprocessing chain on the given file.""" - info = dict(ie_info) - info['filepath'] = filename - for pp in self._pps: - info = pp.run(info) - if info is None: - break - - def _download_with_rtmpdump(self, filename, url, player_url): - self.report_destination(filename) - tmpfilename = self.temp_name(filename) - - # Check for rtmpdump first - try: - subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) - except (OSError, IOError): - self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') - return False - - # Download using rtmpdump. rtmpdump returns exit code 2 when - # the connection was interrumpted and resuming appears to be - # possible. This is part of rtmpdump's normal usage, AFAIK. - basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename] - args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)] - if self.params.get('verbose', False): - try: - import pipes - shell_quote = lambda args: ' '.join(map(pipes.quote, args)) - except ImportError: - shell_quote = repr - self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args)) - retval = subprocess.call(args) - while retval == 2 or retval == 1: - prevsize = os.path.getsize(encodeFilename(tmpfilename)) - self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) - time.sleep(5.0) # This seems to be needed - retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) - cursize = os.path.getsize(encodeFilename(tmpfilename)) - if prevsize == cursize and retval == 1: - break - # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those - if prevsize == cursize and retval == 2 and cursize > 1024: - self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.') - retval = 0 - break - if retval == 0: - self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(encodeFilename(tmpfilename))) - self.try_rename(tmpfilename, filename) - return True - else: - self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) - return False - - def _do_download(self, filename, info_dict): - url = info_dict['url'] - player_url = info_dict.get('player_url', None) - - # Check file already present - if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False): - self.report_file_already_downloaded(filename) - return True - - # Attempt to download using rtmpdump - if url.startswith('rtmp'): - return self._download_with_rtmpdump(filename, url, player_url) - - tmpfilename = self.temp_name(filename) - stream = None - - # Do not include the Accept-Encoding header - headers = {'Youtubedl-no-compression': 'True'} - basic_request = compat_urllib_request.Request(url, None, headers) - request = compat_urllib_request.Request(url, None, headers) - - # Establish possible resume length - if os.path.isfile(encodeFilename(tmpfilename)): - resume_len = os.path.getsize(encodeFilename(tmpfilename)) - else: - resume_len = 0 - - open_mode = 'wb' - if resume_len != 0: - if self.params.get('continuedl', False): - self.report_resuming_byte(resume_len) - request.add_header('Range','bytes=%d-' % resume_len) - open_mode = 'ab' - else: - resume_len = 0 - - count = 0 - retries = self.params.get('retries', 0) - while count <= retries: - # Establish connection - try: - if count == 0 and 'urlhandle' in info_dict: - data = info_dict['urlhandle'] - data = compat_urllib_request.urlopen(request) - break - except (compat_urllib_error.HTTPError, ) as err: - if (err.code < 500 or err.code >= 600) and err.code != 416: - # Unexpected HTTP error - raise - elif err.code == 416: - # Unable to resume (requested range not satisfiable) - try: - # Open the connection again without the range header - data = compat_urllib_request.urlopen(basic_request) - content_length = data.info()['Content-Length'] - except (compat_urllib_error.HTTPError, ) as err: - if err.code < 500 or err.code >= 600: - raise - else: - # Examine the reported length - if (content_length is not None and - (resume_len - 100 < int(content_length) < resume_len + 100)): - # The file had already been fully downloaded. - # Explanation to the above condition: in issue #175 it was revealed that - # YouTube sometimes adds or removes a few bytes from the end of the file, - # changing the file size slightly and causing problems for some users. So - # I decided to implement a suggested change and consider the file - # completely downloaded if the file size differs less than 100 bytes from - # the one in the hard drive. - self.report_file_already_downloaded(filename) - self.try_rename(tmpfilename, filename) - return True - else: - # The length does not match, we start the download over - self.report_unable_to_resume() - open_mode = 'wb' - break - # Retry - count += 1 - if count <= retries: - self.report_retry(count, retries) - - if count > retries: - self.trouble(u'ERROR: giving up after %s retries' % retries) - return False - - data_len = data.info().get('Content-length', None) - if data_len is not None: - data_len = int(data_len) + resume_len - data_len_str = self.format_bytes(data_len) - byte_counter = 0 + resume_len - block_size = self.params.get('buffersize', 1024) - start = time.time() - while True: - # Download and write - before = time.time() - data_block = data.read(block_size) - after = time.time() - if len(data_block) == 0: - break - byte_counter += len(data_block) - - # Open file just in time - if stream is None: - try: - (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) - assert stream is not None - filename = self.undo_temp_name(tmpfilename) - self.report_destination(filename) - except (OSError, IOError) as err: - self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) - return False - try: - stream.write(data_block) - except (IOError, OSError) as err: - self.trouble(u'\nERROR: unable to write data: %s' % str(err)) - return False - if not self.params.get('noresizebuffer', False): - block_size = self.best_block_size(after - before, len(data_block)) - - # Progress message - speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) - if data_len is None: - self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA') - else: - percent_str = self.calc_percent(byte_counter, data_len) - eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) - self.report_progress(percent_str, data_len_str, speed_str, eta_str) - - # Apply rate limit - self.slow_down(start, byte_counter - resume_len) - - if stream is None: - self.trouble(u'\nERROR: Did not get any data blocks') - return False - stream.close() - self.report_finish() - if data_len is not None and byte_counter != data_len: - raise ContentTooShortError(byte_counter, int(data_len)) - self.try_rename(tmpfilename, filename) - - # Update file modification time - if self.params.get('updatetime', True): - info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) - - return True + """File Downloader class. + + File downloader objects are the ones responsible of downloading the + actual video file and writing it to disk if the user has requested + it, among some other tasks. In most cases there should be one per + program. As, given a video URL, the downloader doesn't know how to + extract all the needed information, task that InfoExtractors do, it + has to pass the URL to one of them. + + For this, file downloader objects have a method that allows + InfoExtractors to be registered in a given order. When it is passed + a URL, the file downloader handles it to the first InfoExtractor it + finds that reports being able to handle it. The InfoExtractor extracts + all the information about the video or videos the URL refers to, and + asks the FileDownloader to process the video information, possibly + downloading the video. + + File downloaders accept a lot of parameters. In order not to saturate + the object constructor with arguments, it receives a dictionary of + options instead. These options are available through the params + attribute for the InfoExtractors to use. The FileDownloader also + registers itself as the downloader in charge for the InfoExtractors + that are added to it, so this is a "mutual registration". + + Available options: + + username: Username for authentication purposes. + password: Password for authentication purposes. + usenetrc: Use netrc for authentication instead. + quiet: Do not print messages to stdout. + forceurl: Force printing final URL. + forcetitle: Force printing title. + forcethumbnail: Force printing thumbnail URL. + forcedescription: Force printing description. + forcefilename: Force printing final filename. + simulate: Do not download the video files. + format: Video format code. + format_limit: Highest quality format to try. + outtmpl: Template for output names. + restrictfilenames: Do not allow "&" and spaces in file names + ignoreerrors: Do not stop on download errors. + ratelimit: Download speed limit, in bytes/sec. + nooverwrites: Prevent overwriting files. + retries: Number of times to retry for HTTP error 5xx + buffersize: Size of download buffer in bytes. + noresizebuffer: Do not automatically resize the download buffer. + continuedl: Try to continue downloads if possible. + noprogress: Do not print the progress bar. + playliststart: Playlist item to start at. + playlistend: Playlist item to end at. + matchtitle: Download only matching titles. + rejecttitle: Reject downloads for matching titles. + logtostderr: Log messages to stderr instead of stdout. + consoletitle: Display progress in console window's titlebar. + nopart: Do not use temporary .part files. + updatetime: Use the Last-modified header to set output file timestamps. + writedescription: Write the video description to a .description file + writeinfojson: Write the video description to a .info.json file + writesubtitles: Write the video subtitles to a .srt file + subtitleslang: Language of the subtitles to download + """ + + params = None + _ies = [] + _pps = [] + _download_retcode = None + _num_downloads = None + _screen_file = None + + def __init__(self, params): + """Create a FileDownloader object with the given options.""" + self._ies = [] + self._pps = [] + self._download_retcode = 0 + self._num_downloads = 0 + self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] + self.params = params + + if '%(stitle)s' in self.params['outtmpl']: + self.to_stderr(u'WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') + + @staticmethod + def format_bytes(bytes): + if bytes is None: + return 'N/A' + if type(bytes) is str: + bytes = float(bytes) + if bytes == 0.0: + exponent = 0 + else: + exponent = int(math.log(bytes, 1024.0)) + suffix = 'bkMGTPEZY'[exponent] + converted = float(bytes) / float(1024 ** exponent) + return '%.2f%s' % (converted, suffix) + + @staticmethod + def calc_percent(byte_counter, data_len): + if data_len is None: + return '---.-%' + return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) + + @staticmethod + def calc_eta(start, now, total, current): + if total is None: + return '--:--' + dif = now - start + if current == 0 or dif < 0.001: # One millisecond + return '--:--' + rate = float(current) / dif + eta = int((float(total) - float(current)) / rate) + (eta_mins, eta_secs) = divmod(eta, 60) + if eta_mins > 99: + return '--:--' + return '%02d:%02d' % (eta_mins, eta_secs) + + @staticmethod + def calc_speed(start, now, bytes): + dif = now - start + if bytes == 0 or dif < 0.001: # One millisecond + return '%10s' % '---b/s' + return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) + + @staticmethod + def best_block_size(elapsed_time, bytes): + new_min = max(bytes / 2.0, 1.0) + new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB + if elapsed_time < 0.001: + return int(new_max) + rate = bytes / elapsed_time + if rate > new_max: + return int(new_max) + if rate < new_min: + return int(new_min) + return int(rate) + + @staticmethod + def parse_bytes(bytestr): + """Parse a string indicating a byte quantity into an integer.""" + matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) + if matchobj is None: + return None + number = float(matchobj.group(1)) + multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) + return int(round(number * multiplier)) + + def add_info_extractor(self, ie): + """Add an InfoExtractor object to the end of the list.""" + self._ies.append(ie) + ie.set_downloader(self) + + def add_post_processor(self, pp): + """Add a PostProcessor object to the end of the chain.""" + self._pps.append(pp) + pp.set_downloader(self) + + def to_screen(self, message, skip_eol=False): + """Print message to stdout if not in quiet mode.""" + assert type(message) == type(u'') + if not self.params.get('quiet', False): + terminator = [u'\n', u''][skip_eol] + output = message + terminator + if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr + output = output.encode(preferredencoding(), 'ignore') + self._screen_file.write(output) + self._screen_file.flush() + + def to_stderr(self, message): + """Print message to stderr.""" + assert type(message) == type(u'') + output = message + u'\n' + if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr + output = output.encode(preferredencoding()) + sys.stderr.write(output) + + def to_cons_title(self, message): + """Set console/terminal window title to message.""" + if not self.params.get('consoletitle', False): + return + if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): + # c_wchar_p() might not be necessary if `message` is + # already of type unicode() + ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) + elif 'TERM' in os.environ: + sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding())) + + def fixed_template(self): + """Checks if the output template is fixed.""" + return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None) + + def trouble(self, message=None): + """Determine action to take when a download problem appears. + + Depending on if the downloader has been configured to ignore + download errors or not, this method may throw an exception or + not when errors are found, after printing the message. + """ + if message is not None: + self.to_stderr(message) + if not self.params.get('ignoreerrors', False): + raise DownloadError(message) + self._download_retcode = 1 + + def slow_down(self, start_time, byte_counter): + """Sleep if the download speed is over the rate limit.""" + rate_limit = self.params.get('ratelimit', None) + if rate_limit is None or byte_counter == 0: + return + now = time.time() + elapsed = now - start_time + if elapsed <= 0.0: + return + speed = float(byte_counter) / elapsed + if speed > rate_limit: + time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + + def temp_name(self, filename): + """Returns a temporary filename for the given filename.""" + if self.params.get('nopart', False) or filename == u'-' or \ + (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))): + return filename + return filename + u'.part' + + def undo_temp_name(self, filename): + if filename.endswith(u'.part'): + return filename[:-len(u'.part')] + return filename + + def try_rename(self, old_filename, new_filename): + try: + if old_filename == new_filename: + return + os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) + except (IOError, OSError) as err: + self.trouble(u'ERROR: unable to rename file') + + def try_utime(self, filename, last_modified_hdr): + """Try to set the last-modified time of the given file.""" + if last_modified_hdr is None: + return + if not os.path.isfile(encodeFilename(filename)): + return + timestr = last_modified_hdr + if timestr is None: + return + filetime = timeconvert(timestr) + if filetime is None: + return filetime + try: + os.utime(filename, (time.time(), filetime)) + except: + pass + return filetime + + def report_writedescription(self, descfn): + """ Report that the description file is being written """ + self.to_screen(u'[info] Writing video description to: ' + descfn) + + def report_writesubtitles(self, srtfn): + """ Report that the subtitles file is being written """ + self.to_screen(u'[info] Writing video subtitles to: ' + srtfn) + + def report_writeinfojson(self, infofn): + """ Report that the metadata file has been written """ + self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) + + def report_destination(self, filename): + """Report destination filename.""" + self.to_screen(u'[download] Destination: ' + filename) + + def report_progress(self, percent_str, data_len_str, speed_str, eta_str): + """Report download progress.""" + if self.params.get('noprogress', False): + return + self.to_screen(u'\r[download] %s of %s at %s ETA %s' % + (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) + self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % + (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) + + def report_resuming_byte(self, resume_len): + """Report attempt to resume at given byte.""" + self.to_screen(u'[download] Resuming download at byte %s' % resume_len) + + def report_retry(self, count, retries): + """Report retry in case of HTTP error 5xx""" + self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) + + def report_file_already_downloaded(self, file_name): + """Report file has already been fully downloaded.""" + try: + self.to_screen(u'[download] %s has already been downloaded' % file_name) + except (UnicodeEncodeError) as err: + self.to_screen(u'[download] The file has already been downloaded') + + def report_unable_to_resume(self): + """Report it was impossible to resume download.""" + self.to_screen(u'[download] Unable to resume') + + def report_finish(self): + """Report download finished.""" + if self.params.get('noprogress', False): + self.to_screen(u'[download] Download completed') + else: + self.to_screen(u'') + + def increment_downloads(self): + """Increment the ordinal that assigns a number to each file.""" + self._num_downloads += 1 + + def prepare_filename(self, info_dict): + """Generate the output filename.""" + try: + template_dict = dict(info_dict) + + template_dict['epoch'] = int(time.time()) + template_dict['autonumber'] = u'%05d' % self._num_downloads + + template_dict = dict((key, u'NA' if val is None else val) for key, val in template_dict.items()) + template_dict = dict((k, sanitize_filename(compat_str(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) + + filename = self.params['outtmpl'] % template_dict + return filename + except (ValueError, KeyError) as err: + self.trouble(u'ERROR: invalid system charset or erroneous output template') + return None + + def _match_entry(self, info_dict): + """ Returns None iff the file should be downloaded """ + + title = info_dict['title'] + matchtitle = self.params.get('matchtitle', False) + if matchtitle: + matchtitle = matchtitle.decode('utf8') + if not re.search(matchtitle, title, re.IGNORECASE): + return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' + rejecttitle = self.params.get('rejecttitle', False) + if rejecttitle: + rejecttitle = rejecttitle.decode('utf8') + if re.search(rejecttitle, title, re.IGNORECASE): + return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' + return None + + def process_info(self, info_dict): + """Process a single dictionary returned by an InfoExtractor.""" + + # Keep for backwards compatibility + info_dict['stitle'] = info_dict['title'] + + if not 'format' in info_dict: + info_dict['format'] = info_dict['ext'] + + reason = self._match_entry(info_dict) + if reason is not None: + self.to_screen(u'[download] ' + reason) + return + + max_downloads = self.params.get('max_downloads') + if max_downloads is not None: + if self._num_downloads > int(max_downloads): + raise MaxDownloadsReached() + + filename = self.prepare_filename(info_dict) + + # Forced printings + if self.params.get('forcetitle', False): + compat_print(info_dict['title']) + if self.params.get('forceurl', False): + compat_print(info_dict['url']) + if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: + compat_print(info_dict['thumbnail']) + if self.params.get('forcedescription', False) and 'description' in info_dict: + compat_print(info_dict['description']) + if self.params.get('forcefilename', False) and filename is not None: + compat_print(filename) + if self.params.get('forceformat', False): + compat_print(info_dict['format']) + + # Do nothing else if in simulate mode + if self.params.get('simulate', False): + return + + if filename is None: + return + + try: + dn = os.path.dirname(encodeFilename(filename)) + if dn != '' and not os.path.exists(dn): # dn is already encoded + os.makedirs(dn) + except (OSError, IOError) as err: + self.trouble(u'ERROR: unable to create directory ' + compat_str(err)) + return + + if self.params.get('writedescription', False): + try: + descfn = filename + u'.description' + self.report_writedescription(descfn) + descfile = open(encodeFilename(descfn), 'wb') + try: + descfile.write(info_dict['description'].encode('utf-8')) + finally: + descfile.close() + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write description file ' + descfn) + return + + if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: + # subtitles download errors are already managed as troubles in relevant IE + # that way it will silently go on when used with unsupporting IE + try: + srtfn = filename.rsplit('.', 1)[0] + u'.srt' + self.report_writesubtitles(srtfn) + srtfile = open(encodeFilename(srtfn), 'wb') + try: + srtfile.write(info_dict['subtitles'].encode('utf-8')) + finally: + srtfile.close() + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write subtitles file ' + descfn) + return + + if self.params.get('writeinfojson', False): + infofn = filename + u'.info.json' + self.report_writeinfojson(infofn) + try: + json.dump + except (NameError,AttributeError): + self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') + return + try: + infof = open(encodeFilename(infofn), 'wb') + try: + json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',)) + json.dump(json_info_dict, infof) + finally: + infof.close() + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) + return + + if not self.params.get('skip_download', False): + if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): + success = True + else: + try: + success = self._do_download(filename, info_dict) + except (OSError, IOError) as err: + raise UnavailableVideoError + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self.trouble(u'ERROR: unable to download video data: %s' % str(err)) + return + except (ContentTooShortError, ) as err: + self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + return + + if success: + try: + self.post_process(filename, info_dict) + except (PostProcessingError) as err: + self.trouble(u'ERROR: postprocessing: %s' % str(err)) + return + + def download(self, url_list): + """Download a given list of URLs.""" + if len(url_list) > 1 and self.fixed_template(): + raise SameFileError(self.params['outtmpl']) + + for url in url_list: + suitable_found = False + for ie in self._ies: + # Go to next InfoExtractor if not suitable + if not ie.suitable(url): + continue + + # Warn if the _WORKING attribute is False + if not ie.working(): + self.trouble(u'WARNING: the program functionality for this site has been marked as broken, ' + u'and will probably not work. If you want to go on, use the -i option.') + + # Suitable InfoExtractor found + suitable_found = True + + # Extract information from URL and process it + videos = ie.extract(url) + for video in videos or []: + video['extractor'] = ie.IE_NAME + try: + self.increment_downloads() + self.process_info(video) + except UnavailableVideoError: + self.trouble(u'\nERROR: unable to download video') + + # Suitable InfoExtractor had been found; go to next URL + break + + if not suitable_found: + self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) + + return self._download_retcode + + def post_process(self, filename, ie_info): + """Run the postprocessing chain on the given file.""" + info = dict(ie_info) + info['filepath'] = filename + for pp in self._pps: + info = pp.run(info) + if info is None: + break + + def _download_with_rtmpdump(self, filename, url, player_url): + self.report_destination(filename) + tmpfilename = self.temp_name(filename) + + # Check for rtmpdump first + try: + subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) + except (OSError, IOError): + self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') + return False + + # Download using rtmpdump. rtmpdump returns exit code 2 when + # the connection was interrumpted and resuming appears to be + # possible. This is part of rtmpdump's normal usage, AFAIK. + basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename] + args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)] + if self.params.get('verbose', False): + try: + import pipes + shell_quote = lambda args: ' '.join(map(pipes.quote, args)) + except ImportError: + shell_quote = repr + self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args)) + retval = subprocess.call(args) + while retval == 2 or retval == 1: + prevsize = os.path.getsize(encodeFilename(tmpfilename)) + self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) + time.sleep(5.0) # This seems to be needed + retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) + cursize = os.path.getsize(encodeFilename(tmpfilename)) + if prevsize == cursize and retval == 1: + break + # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those + if prevsize == cursize and retval == 2 and cursize > 1024: + self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.') + retval = 0 + break + if retval == 0: + self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(encodeFilename(tmpfilename))) + self.try_rename(tmpfilename, filename) + return True + else: + self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) + return False + + def _do_download(self, filename, info_dict): + url = info_dict['url'] + player_url = info_dict.get('player_url', None) + + # Check file already present + if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False): + self.report_file_already_downloaded(filename) + return True + + # Attempt to download using rtmpdump + if url.startswith('rtmp'): + return self._download_with_rtmpdump(filename, url, player_url) + + tmpfilename = self.temp_name(filename) + stream = None + + # Do not include the Accept-Encoding header + headers = {'Youtubedl-no-compression': 'True'} + basic_request = compat_urllib_request.Request(url, None, headers) + request = compat_urllib_request.Request(url, None, headers) + + # Establish possible resume length + if os.path.isfile(encodeFilename(tmpfilename)): + resume_len = os.path.getsize(encodeFilename(tmpfilename)) + else: + resume_len = 0 + + open_mode = 'wb' + if resume_len != 0: + if self.params.get('continuedl', False): + self.report_resuming_byte(resume_len) + request.add_header('Range','bytes=%d-' % resume_len) + open_mode = 'ab' + else: + resume_len = 0 + + count = 0 + retries = self.params.get('retries', 0) + while count <= retries: + # Establish connection + try: + if count == 0 and 'urlhandle' in info_dict: + data = info_dict['urlhandle'] + data = compat_urllib_request.urlopen(request) + break + except (compat_urllib_error.HTTPError, ) as err: + if (err.code < 500 or err.code >= 600) and err.code != 416: + # Unexpected HTTP error + raise + elif err.code == 416: + # Unable to resume (requested range not satisfiable) + try: + # Open the connection again without the range header + data = compat_urllib_request.urlopen(basic_request) + content_length = data.info()['Content-Length'] + except (compat_urllib_error.HTTPError, ) as err: + if err.code < 500 or err.code >= 600: + raise + else: + # Examine the reported length + if (content_length is not None and + (resume_len - 100 < int(content_length) < resume_len + 100)): + # The file had already been fully downloaded. + # Explanation to the above condition: in issue #175 it was revealed that + # YouTube sometimes adds or removes a few bytes from the end of the file, + # changing the file size slightly and causing problems for some users. So + # I decided to implement a suggested change and consider the file + # completely downloaded if the file size differs less than 100 bytes from + # the one in the hard drive. + self.report_file_already_downloaded(filename) + self.try_rename(tmpfilename, filename) + return True + else: + # The length does not match, we start the download over + self.report_unable_to_resume() + open_mode = 'wb' + break + # Retry + count += 1 + if count <= retries: + self.report_retry(count, retries) + + if count > retries: + self.trouble(u'ERROR: giving up after %s retries' % retries) + return False + + data_len = data.info().get('Content-length', None) + if data_len is not None: + data_len = int(data_len) + resume_len + data_len_str = self.format_bytes(data_len) + byte_counter = 0 + resume_len + block_size = self.params.get('buffersize', 1024) + start = time.time() + while True: + # Download and write + before = time.time() + data_block = data.read(block_size) + after = time.time() + if len(data_block) == 0: + break + byte_counter += len(data_block) + + # Open file just in time + if stream is None: + try: + (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) + assert stream is not None + filename = self.undo_temp_name(tmpfilename) + self.report_destination(filename) + except (OSError, IOError) as err: + self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) + return False + try: + stream.write(data_block) + except (IOError, OSError) as err: + self.trouble(u'\nERROR: unable to write data: %s' % str(err)) + return False + if not self.params.get('noresizebuffer', False): + block_size = self.best_block_size(after - before, len(data_block)) + + # Progress message + speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) + if data_len is None: + self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA') + else: + percent_str = self.calc_percent(byte_counter, data_len) + eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) + self.report_progress(percent_str, data_len_str, speed_str, eta_str) + + # Apply rate limit + self.slow_down(start, byte_counter - resume_len) + + if stream is None: + self.trouble(u'\nERROR: Did not get any data blocks') + return False + stream.close() + self.report_finish() + if data_len is not None and byte_counter != data_len: + raise ContentTooShortError(byte_counter, int(data_len)) + self.try_rename(tmpfilename, filename) + + # Update file modification time + if self.params.get('updatetime', True): + info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) + + return True diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 94803aa95..d1b239abf 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -16,3553 +16,3553 @@ from utils import * class InfoExtractor(object): - """Information Extractor class. + """Information Extractor class. - Information extractors are the classes that, given a URL, extract - information about the video (or videos) the URL refers to. This - information includes the real video URL, the video title, author and - others. The information is stored in a dictionary which is then - passed to the FileDownloader. The FileDownloader processes this - information possibly downloading the video to the file system, among - other possible outcomes. + Information extractors are the classes that, given a URL, extract + information about the video (or videos) the URL refers to. This + information includes the real video URL, the video title, author and + others. The information is stored in a dictionary which is then + passed to the FileDownloader. The FileDownloader processes this + information possibly downloading the video to the file system, among + other possible outcomes. - The dictionaries must include the following fields: + The dictionaries must include the following fields: - id: Video identifier. - url: Final video URL. - uploader: Nickname of the video uploader, unescaped. - upload_date: Video upload date (YYYYMMDD). - title: Video title, unescaped. - ext: Video filename extension. + id: Video identifier. + url: Final video URL. + uploader: Nickname of the video uploader, unescaped. + upload_date: Video upload date (YYYYMMDD). + title: Video title, unescaped. + ext: Video filename extension. - The following fields are optional: + The following fields are optional: - format: The video format, defaults to ext (used for --get-format) - thumbnail: Full URL to a video thumbnail image. - description: One-line video description. - player_url: SWF Player URL (used for rtmpdump). - subtitles: The .srt file contents. - urlhandle: [internal] The urlHandle to be used to download the file, - like returned by urllib.request.urlopen + format: The video format, defaults to ext (used for --get-format) + thumbnail: Full URL to a video thumbnail image. + description: One-line video description. + player_url: SWF Player URL (used for rtmpdump). + subtitles: The .srt file contents. + urlhandle: [internal] The urlHandle to be used to download the file, + like returned by urllib.request.urlopen - The fields should all be Unicode strings. + The fields should all be Unicode strings. - Subclasses of this one should re-define the _real_initialize() and - _real_extract() methods and define a _VALID_URL regexp. - Probably, they should also be added to the list of extractors. + Subclasses of this one should re-define the _real_initialize() and + _real_extract() methods and define a _VALID_URL regexp. + Probably, they should also be added to the list of extractors. - _real_extract() must return a *list* of information dictionaries as - described above. + _real_extract() must return a *list* of information dictionaries as + described above. - Finally, the _WORKING attribute should be set to False for broken IEs - in order to warn the users and skip the tests. - """ + Finally, the _WORKING attribute should be set to False for broken IEs + in order to warn the users and skip the tests. + """ - _ready = False - _downloader = None - _WORKING = True + _ready = False + _downloader = None + _WORKING = True - def __init__(self, downloader=None): - """Constructor. Receives an optional downloader.""" - self._ready = False - self.set_downloader(downloader) + def __init__(self, downloader=None): + """Constructor. Receives an optional downloader.""" + self._ready = False + self.set_downloader(downloader) - def suitable(self, url): - """Receives a URL and returns True if suitable for this IE.""" - return re.match(self._VALID_URL, url) is not None + def suitable(self, url): + """Receives a URL and returns True if suitable for this IE.""" + return re.match(self._VALID_URL, url) is not None - def working(self): - """Getter method for _WORKING.""" - return self._WORKING + def working(self): + """Getter method for _WORKING.""" + return self._WORKING - def initialize(self): - """Initializes an instance (authentication, etc).""" - if not self._ready: - self._real_initialize() - self._ready = True + def initialize(self): + """Initializes an instance (authentication, etc).""" + if not self._ready: + self._real_initialize() + self._ready = True - def extract(self, url): - """Extracts URL information and returns it in list of dicts.""" - self.initialize() - return self._real_extract(url) + def extract(self, url): + """Extracts URL information and returns it in list of dicts.""" + self.initialize() + return self._real_extract(url) - def set_downloader(self, downloader): - """Sets the downloader for this IE.""" - self._downloader = downloader + def set_downloader(self, downloader): + """Sets the downloader for this IE.""" + self._downloader = downloader - def _real_initialize(self): - """Real initialization process. Redefine in subclasses.""" - pass + def _real_initialize(self): + """Real initialization process. Redefine in subclasses.""" + pass - def _real_extract(self, url): - """Real extraction process. Redefine in subclasses.""" - pass + def _real_extract(self, url): + """Real extraction process. Redefine in subclasses.""" + pass class YoutubeIE(InfoExtractor): - """Information extractor for youtube.com.""" - - _VALID_URL = r"""^ - ( - (?:https?://)? # http(s):// (optional) - (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| - tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains - (?:.*?\#/)? # handle anchor (#/) redirect urls - (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs - (?: # the various things that can precede the ID: - (?:(?:v|embed|e)/) # v/ or embed/ or e/ - |(?: # or the v= param in all its forms - (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) - (?:\?|\#!?) # the params delimiter ? or # or #! - (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx) - v= - ) - )? # optional -> youtube.com/xxxx is OK - )? # all until now is optional -> you can pass the naked ID - ([0-9A-Za-z_-]+) # here is it! the YouTube video ID - (?(1).+)? # if we found the ID, everything can follow - $""" - _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' - _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' - _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' - _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' - _NETRC_MACHINE = 'youtube' - # Listed in order of quality - _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] - _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] - _video_extensions = { - '13': '3gp', - '17': 'mp4', - '18': 'mp4', - '22': 'mp4', - '37': 'mp4', - '38': 'video', # You actually don't know if this will be MOV, AVI or whatever - '43': 'webm', - '44': 'webm', - '45': 'webm', - '46': 'webm', - } - _video_dimensions = { - '5': '240x400', - '6': '???', - '13': '???', - '17': '144x176', - '18': '360x640', - '22': '720x1280', - '34': '360x640', - '35': '480x854', - '37': '1080x1920', - '38': '3072x4096', - '43': '360x640', - '44': '480x854', - '45': '720x1280', - '46': '1080x1920', - } - IE_NAME = u'youtube' - - def suitable(self, url): - """Receives a URL and returns True if suitable for this IE.""" - return re.match(self._VALID_URL, url, re.VERBOSE) is not None - - def report_lang(self): - """Report attempt to set language.""" - self._downloader.to_screen(u'[youtube] Setting language') - - def report_login(self): - """Report attempt to log in.""" - self._downloader.to_screen(u'[youtube] Logging in') - - def report_age_confirmation(self): - """Report attempt to confirm age.""" - self._downloader.to_screen(u'[youtube] Confirming age') - - def report_video_webpage_download(self, video_id): - """Report attempt to download video webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) - - def report_video_info_webpage_download(self, video_id): - """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) - - def report_video_subtitles_download(self, video_id): - """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id) - - def report_information_extraction(self, video_id): - """Report attempt to extract video information.""" - self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) - - def report_unavailable_format(self, video_id, format): - """Report extracted video URL.""" - self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) - - def report_rtmp_download(self): - """Indicate the download will use the RTMP protocol.""" - self._downloader.to_screen(u'[youtube] RTMP download detected') - - def _closed_captions_xml_to_srt(self, xml_string): - srt = '' - texts = re.findall(r'([^<]+)', xml_string, re.MULTILINE) - # TODO parse xml instead of regex - for n, (start, dur_tag, dur, caption) in enumerate(texts): - if not dur: dur = '4' - start = float(start) - end = start + float(dur) - start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) - end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) - caption = unescapeHTML(caption) - caption = unescapeHTML(caption) # double cycle, intentional - srt += str(n+1) + '\n' - srt += start + ' --> ' + end + '\n' - srt += caption + '\n\n' - return srt - - def _print_formats(self, formats): - print('Available formats:') - for x in formats: - print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))) - - def _real_initialize(self): - if self._downloader is None: - return - - username = None - password = None - downloader_params = self._downloader.params - - # Attempt to use provided username and password or .netrc data - if downloader_params.get('username', None) is not None: - username = downloader_params['username'] - password = downloader_params['password'] - elif downloader_params.get('usenetrc', False): - try: - info = netrc.netrc().authenticators(self._NETRC_MACHINE) - if info is not None: - username = info[0] - password = info[2] - else: - raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) - except (IOError, netrc.NetrcParseError) as err: - self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) - return - - # Set language - request = compat_urllib_request.Request(self._LANG_URL) - try: - self.report_lang() - compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err)) - return - - # No authentication to be performed - if username is None: - return - - # Log in - login_form = { - 'current_form': 'loginForm', - 'next': '/', - 'action_login': 'Log In', - 'username': username, - 'password': password, - } - request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) - try: - self.report_login() - login_results = compat_urllib_request.urlopen(request).read() - if re.search(r'(?i)]* name="loginForm"', login_results) is not None: - self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') - return - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err)) - return - - # Confirm age - age_form = { - 'next_url': '/', - 'action_confirm': 'Confirm', - } - request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form)) - try: - self.report_age_confirmation() - age_results = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) - return - - def _real_extract(self, url): - # Extract original video URL from URL with redirection, like age verification, using next_url parameter - mobj = re.search(self._NEXT_URL_RE, url) - if mobj: - url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') - - # Extract video id from URL - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - video_id = mobj.group(2) - - # Get video webpage - self.report_video_webpage_download(video_id) - request = compat_urllib_request.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) - try: - video_webpage_bytes = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) - return - - video_webpage = video_webpage_bytes.decode('utf-8', 'ignore') - - # Attempt to extract SWF player URL - mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) - if mobj is not None: - player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) - else: - player_url = None - - # Get video info - self.report_video_info_webpage_download(video_id) - for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: - video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' - % (video_id, el_type)) - request = compat_urllib_request.Request(video_info_url) - try: - video_info_webpage_bytes = compat_urllib_request.urlopen(request).read() - video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore') - video_info = compat_parse_qs(video_info_webpage) - if 'token' in video_info: - break - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) - return - if 'token' not in video_info: - if 'reason' in video_info: - self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0]) - else: - self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') - return - - # Check for "rental" videos - if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: - self._downloader.trouble(u'ERROR: "rental" videos not supported') - return - - # Start extracting information - self.report_information_extraction(video_id) - - # uploader - if 'author' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') - return - video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) - - # title - if 'title' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = compat_urllib_parse.unquote_plus(video_info['title'][0]) - - # thumbnail image - if 'thumbnail_url' not in video_info: - self._downloader.trouble(u'WARNING: unable to extract video thumbnail') - video_thumbnail = '' - else: # don't panic if we can't find it - video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) - - # upload date - upload_date = None - mobj = re.search(r'id="eow-date.*?>(.*?)', video_webpage, re.DOTALL) - if mobj is not None: - upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) - format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] - for expression in format_expressions: - try: - upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') - except: - pass - - # description - video_description = get_element_by_id("eow-description", video_webpage) - if video_description: - video_description = clean_html(video_description) - else: - video_description = '' - - # closed captions - video_subtitles = None - if self._downloader.params.get('writesubtitles', False): - try: - self.report_video_subtitles_download(video_id) - request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) - try: - srt_list = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err)) - srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list) - srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list) - if not srt_lang_list: - raise Trouble(u'WARNING: video has no closed captions') - if self._downloader.params.get('subtitleslang', False): - srt_lang = self._downloader.params.get('subtitleslang') - elif 'en' in srt_lang_list: - srt_lang = 'en' - else: - srt_lang = srt_lang_list.keys()[0] - if not srt_lang in srt_lang_list: - raise Trouble(u'WARNING: no closed captions found in the specified language') - request = compat_urllib_request.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id)) - try: - srt_xml = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err)) - if not srt_xml: - raise Trouble(u'WARNING: unable to download video subtitles') - video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8')) - except Trouble as trouble: - self._downloader.trouble(trouble[0]) - - if 'length_seconds' not in video_info: - self._downloader.trouble(u'WARNING: unable to extract video duration') - video_duration = '' - else: - video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]) - - # token - video_token = compat_urllib_parse.unquote_plus(video_info['token'][0]) - - # Decide which formats to download - req_format = self._downloader.params.get('format', None) - - if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): - self.report_rtmp_download() - video_url_list = [(None, video_info['conn'][0])] - elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: - url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') - url_data = [compat_parse_qs(uds) for uds in url_data_strs] - url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data) - url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data) - - format_limit = self._downloader.params.get('format_limit', None) - available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats - if format_limit is not None and format_limit in available_formats: - format_list = available_formats[available_formats.index(format_limit):] - else: - format_list = available_formats - existing_formats = [x for x in format_list if x in url_map] - if len(existing_formats) == 0: - self._downloader.trouble(u'ERROR: no known formats available for video') - return - if self._downloader.params.get('listformats', None): - self._print_formats(existing_formats) - return - if req_format is None or req_format == 'best': - video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality - elif req_format == 'worst': - video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality - elif req_format in ('-1', 'all'): - video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats - else: - # Specific formats. We pick the first in a slash-delimeted sequence. - # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. - req_formats = req_format.split('/') - video_url_list = None - for rf in req_formats: - if rf in url_map: - video_url_list = [(rf, url_map[rf])] - break - if video_url_list is None: - self._downloader.trouble(u'ERROR: requested format not available') - return - else: - self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') - return - - results = [] - for format_param, video_real_url in video_url_list: - # Extension - video_extension = self._video_extensions.get(format_param, 'flv') - - video_format = '{} - {}'.format(format_param if format_param else video_extension, - self._video_dimensions.get(format_param, '???')) - - results.append({ - 'id': video_id, - 'url': video_real_url, - 'uploader': video_uploader, - 'upload_date': upload_date, - 'title': video_title, - 'ext': video_extension, - 'format': video_format, - 'thumbnail': video_thumbnail, - 'description': video_description, - 'player_url': player_url, - 'subtitles': video_subtitles, - 'duration': video_duration - }) - return results + """Information extractor for youtube.com.""" + + _VALID_URL = r"""^ + ( + (?:https?://)? # http(s):// (optional) + (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| + tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains + (?:.*?\#/)? # handle anchor (#/) redirect urls + (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs + (?: # the various things that can precede the ID: + (?:(?:v|embed|e)/) # v/ or embed/ or e/ + |(?: # or the v= param in all its forms + (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) + (?:\?|\#!?) # the params delimiter ? or # or #! + (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx) + v= + ) + )? # optional -> youtube.com/xxxx is OK + )? # all until now is optional -> you can pass the naked ID + ([0-9A-Za-z_-]+) # here is it! the YouTube video ID + (?(1).+)? # if we found the ID, everything can follow + $""" + _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' + _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' + _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' + _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' + _NETRC_MACHINE = 'youtube' + # Listed in order of quality + _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] + _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] + _video_extensions = { + '13': '3gp', + '17': 'mp4', + '18': 'mp4', + '22': 'mp4', + '37': 'mp4', + '38': 'video', # You actually don't know if this will be MOV, AVI or whatever + '43': 'webm', + '44': 'webm', + '45': 'webm', + '46': 'webm', + } + _video_dimensions = { + '5': '240x400', + '6': '???', + '13': '???', + '17': '144x176', + '18': '360x640', + '22': '720x1280', + '34': '360x640', + '35': '480x854', + '37': '1080x1920', + '38': '3072x4096', + '43': '360x640', + '44': '480x854', + '45': '720x1280', + '46': '1080x1920', + } + IE_NAME = u'youtube' + + def suitable(self, url): + """Receives a URL and returns True if suitable for this IE.""" + return re.match(self._VALID_URL, url, re.VERBOSE) is not None + + def report_lang(self): + """Report attempt to set language.""" + self._downloader.to_screen(u'[youtube] Setting language') + + def report_login(self): + """Report attempt to log in.""" + self._downloader.to_screen(u'[youtube] Logging in') + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self._downloader.to_screen(u'[youtube] Confirming age') + + def report_video_webpage_download(self, video_id): + """Report attempt to download video webpage.""" + self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) + + def report_video_info_webpage_download(self, video_id): + """Report attempt to download video info webpage.""" + self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) + + def report_video_subtitles_download(self, video_id): + """Report attempt to download video info webpage.""" + self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id) + + def report_information_extraction(self, video_id): + """Report attempt to extract video information.""" + self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) + + def report_unavailable_format(self, video_id, format): + """Report extracted video URL.""" + self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) + + def report_rtmp_download(self): + """Indicate the download will use the RTMP protocol.""" + self._downloader.to_screen(u'[youtube] RTMP download detected') + + def _closed_captions_xml_to_srt(self, xml_string): + srt = '' + texts = re.findall(r'([^<]+)', xml_string, re.MULTILINE) + # TODO parse xml instead of regex + for n, (start, dur_tag, dur, caption) in enumerate(texts): + if not dur: dur = '4' + start = float(start) + end = start + float(dur) + start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) + end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) + caption = unescapeHTML(caption) + caption = unescapeHTML(caption) # double cycle, intentional + srt += str(n+1) + '\n' + srt += start + ' --> ' + end + '\n' + srt += caption + '\n\n' + return srt + + def _print_formats(self, formats): + print('Available formats:') + for x in formats: + print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))) + + def _real_initialize(self): + if self._downloader is None: + return + + username = None + password = None + downloader_params = self._downloader.params + + # Attempt to use provided username and password or .netrc data + if downloader_params.get('username', None) is not None: + username = downloader_params['username'] + password = downloader_params['password'] + elif downloader_params.get('usenetrc', False): + try: + info = netrc.netrc().authenticators(self._NETRC_MACHINE) + if info is not None: + username = info[0] + password = info[2] + else: + raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) + except (IOError, netrc.NetrcParseError) as err: + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) + return + + # Set language + request = compat_urllib_request.Request(self._LANG_URL) + try: + self.report_lang() + compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err)) + return + + # No authentication to be performed + if username is None: + return + + # Log in + login_form = { + 'current_form': 'loginForm', + 'next': '/', + 'action_login': 'Log In', + 'username': username, + 'password': password, + } + request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) + try: + self.report_login() + login_results = compat_urllib_request.urlopen(request).read() + if re.search(r'(?i)]* name="loginForm"', login_results) is not None: + self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') + return + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err)) + return + + # Confirm age + age_form = { + 'next_url': '/', + 'action_confirm': 'Confirm', + } + request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form)) + try: + self.report_age_confirmation() + age_results = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) + return + + def _real_extract(self, url): + # Extract original video URL from URL with redirection, like age verification, using next_url parameter + mobj = re.search(self._NEXT_URL_RE, url) + if mobj: + url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') + + # Extract video id from URL + mobj = re.match(self._VALID_URL, url, re.VERBOSE) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group(2) + + # Get video webpage + self.report_video_webpage_download(video_id) + request = compat_urllib_request.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) + try: + video_webpage_bytes = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) + return + + video_webpage = video_webpage_bytes.decode('utf-8', 'ignore') + + # Attempt to extract SWF player URL + mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) + if mobj is not None: + player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) + else: + player_url = None + + # Get video info + self.report_video_info_webpage_download(video_id) + for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: + video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' + % (video_id, el_type)) + request = compat_urllib_request.Request(video_info_url) + try: + video_info_webpage_bytes = compat_urllib_request.urlopen(request).read() + video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore') + video_info = compat_parse_qs(video_info_webpage) + if 'token' in video_info: + break + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) + return + if 'token' not in video_info: + if 'reason' in video_info: + self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0]) + else: + self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') + return + + # Check for "rental" videos + if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: + self._downloader.trouble(u'ERROR: "rental" videos not supported') + return + + # Start extracting information + self.report_information_extraction(video_id) + + # uploader + if 'author' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) + + # title + if 'title' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = compat_urllib_parse.unquote_plus(video_info['title'][0]) + + # thumbnail image + if 'thumbnail_url' not in video_info: + self._downloader.trouble(u'WARNING: unable to extract video thumbnail') + video_thumbnail = '' + else: # don't panic if we can't find it + video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) + + # upload date + upload_date = None + mobj = re.search(r'id="eow-date.*?>(.*?)', video_webpage, re.DOTALL) + if mobj is not None: + upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) + format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] + for expression in format_expressions: + try: + upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') + except: + pass + + # description + video_description = get_element_by_id("eow-description", video_webpage) + if video_description: + video_description = clean_html(video_description) + else: + video_description = '' + + # closed captions + video_subtitles = None + if self._downloader.params.get('writesubtitles', False): + try: + self.report_video_subtitles_download(video_id) + request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) + try: + srt_list = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err)) + srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list) + srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list) + if not srt_lang_list: + raise Trouble(u'WARNING: video has no closed captions') + if self._downloader.params.get('subtitleslang', False): + srt_lang = self._downloader.params.get('subtitleslang') + elif 'en' in srt_lang_list: + srt_lang = 'en' + else: + srt_lang = srt_lang_list.keys()[0] + if not srt_lang in srt_lang_list: + raise Trouble(u'WARNING: no closed captions found in the specified language') + request = compat_urllib_request.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id)) + try: + srt_xml = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err)) + if not srt_xml: + raise Trouble(u'WARNING: unable to download video subtitles') + video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8')) + except Trouble as trouble: + self._downloader.trouble(trouble[0]) + + if 'length_seconds' not in video_info: + self._downloader.trouble(u'WARNING: unable to extract video duration') + video_duration = '' + else: + video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]) + + # token + video_token = compat_urllib_parse.unquote_plus(video_info['token'][0]) + + # Decide which formats to download + req_format = self._downloader.params.get('format', None) + + if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): + self.report_rtmp_download() + video_url_list = [(None, video_info['conn'][0])] + elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: + url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') + url_data = [compat_parse_qs(uds) for uds in url_data_strs] + url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data) + url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data) + + format_limit = self._downloader.params.get('format_limit', None) + available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats + if format_limit is not None and format_limit in available_formats: + format_list = available_formats[available_formats.index(format_limit):] + else: + format_list = available_formats + existing_formats = [x for x in format_list if x in url_map] + if len(existing_formats) == 0: + self._downloader.trouble(u'ERROR: no known formats available for video') + return + if self._downloader.params.get('listformats', None): + self._print_formats(existing_formats) + return + if req_format is None or req_format == 'best': + video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality + elif req_format == 'worst': + video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality + elif req_format in ('-1', 'all'): + video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats + else: + # Specific formats. We pick the first in a slash-delimeted sequence. + # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. + req_formats = req_format.split('/') + video_url_list = None + for rf in req_formats: + if rf in url_map: + video_url_list = [(rf, url_map[rf])] + break + if video_url_list is None: + self._downloader.trouble(u'ERROR: requested format not available') + return + else: + self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') + return + + results = [] + for format_param, video_real_url in video_url_list: + # Extension + video_extension = self._video_extensions.get(format_param, 'flv') + + video_format = '{} - {}'.format(format_param if format_param else video_extension, + self._video_dimensions.get(format_param, '???')) + + results.append({ + 'id': video_id, + 'url': video_real_url, + 'uploader': video_uploader, + 'upload_date': upload_date, + 'title': video_title, + 'ext': video_extension, + 'format': video_format, + 'thumbnail': video_thumbnail, + 'description': video_description, + 'player_url': player_url, + 'subtitles': video_subtitles, + 'duration': video_duration + }) + return results class MetacafeIE(InfoExtractor): - """Information Extractor for metacafe.com.""" - - _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' - _DISCLAIMER = 'http://www.metacafe.com/family_filter/' - _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' - IE_NAME = u'metacafe' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_disclaimer(self): - """Report disclaimer retrieval.""" - self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') - - def report_age_confirmation(self): - """Report attempt to confirm age.""" - self._downloader.to_screen(u'[metacafe] Confirming age') - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) - - def _real_initialize(self): - # Retrieve disclaimer - request = compat_urllib_request.Request(self._DISCLAIMER) - try: - self.report_disclaimer() - disclaimer = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err)) - return - - # Confirm age - disclaimer_form = { - 'filters': '0', - 'submit': "Continue - I'm over 18", - } - request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) - try: - self.report_age_confirmation() - disclaimer = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) - return - - def _real_extract(self, url): - # Extract id and simplified title from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - - video_id = mobj.group(1) - - # Check if video comes from YouTube - mobj2 = re.match(r'^yt-(.*)$', video_id) - if mobj2 is not None: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)]) - return - - # Retrieve video webpage to extract further information - request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) - return - - # Extract URL, uploader and title from webpage - self.report_extraction(video_id) - mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) - if mobj is not None: - mediaURL = compat_urllib_parse.unquote(mobj.group(1)) - video_extension = mediaURL[-3:] - - # Extract gdaKey if available - mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) - if mobj is None: - video_url = mediaURL - else: - gdaKey = mobj.group(1) - video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - else: - mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - vardict = compat_parse_qs(mobj.group(1)) - if 'mediaData' not in vardict: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - mediaURL = mobj.group(1).replace('\\/', '/') - video_extension = mediaURL[-3:] - video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) - - mobj = re.search(r'(?im)(.*) - Video', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - video_title = mobj.group(1).decode('utf-8') - - mobj = re.search(r'submitter=(.*?);', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') - return - video_uploader = mobj.group(1) - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader.decode('utf-8'), - 'upload_date': None, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - }] + """Information Extractor for metacafe.com.""" + + _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' + _DISCLAIMER = 'http://www.metacafe.com/family_filter/' + _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' + IE_NAME = u'metacafe' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_disclaimer(self): + """Report disclaimer retrieval.""" + self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self._downloader.to_screen(u'[metacafe] Confirming age') + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) + + def _real_initialize(self): + # Retrieve disclaimer + request = compat_urllib_request.Request(self._DISCLAIMER) + try: + self.report_disclaimer() + disclaimer = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err)) + return + + # Confirm age + disclaimer_form = { + 'filters': '0', + 'submit': "Continue - I'm over 18", + } + request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) + try: + self.report_age_confirmation() + disclaimer = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) + return + + def _real_extract(self, url): + # Extract id and simplified title from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + # Check if video comes from YouTube + mobj2 = re.match(r'^yt-(.*)$', video_id) + if mobj2 is not None: + self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)]) + return + + # Retrieve video webpage to extract further information + request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) + try: + self.report_download_webpage(video_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) + return + + # Extract URL, uploader and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) + if mobj is not None: + mediaURL = compat_urllib_parse.unquote(mobj.group(1)) + video_extension = mediaURL[-3:] + + # Extract gdaKey if available + mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) + if mobj is None: + video_url = mediaURL + else: + gdaKey = mobj.group(1) + video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) + else: + mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + vardict = compat_parse_qs(mobj.group(1)) + if 'mediaData' not in vardict: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = mobj.group(1).replace('\\/', '/') + video_extension = mediaURL[-3:] + video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) + + mobj = re.search(r'(?im)(.*) - Video', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1).decode('utf-8') + + mobj = re.search(r'submitter=(.*?);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = mobj.group(1) + + return [{ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'upload_date': None, + 'title': video_title, + 'ext': video_extension.decode('utf-8'), + }] class DailymotionIE(InfoExtractor): - """Information Extractor for Dailymotion""" - - _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' - IE_NAME = u'dailymotion' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) - - def _real_extract(self, url): - # Extract id and simplified title from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: invalid URL: %s' % url) - return - - video_id = mobj.group(1).split('_')[0].split('?')[0] - - video_extension = 'mp4' - - # Retrieve video webpage to extract further information - request = compat_urllib_request.Request(url) - request.add_header('Cookie', 'family_filter=off') - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) - return - - # Extract URL, uploader and title from webpage - self.report_extraction(video_id) - mobj = re.search(r'\s*var flashvars = (.*)', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - flashvars = compat_urllib_parse.unquote(mobj.group(1)) - - for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: - if key in flashvars: - max_quality = key - self._downloader.to_screen(u'[dailymotion] Using %s' % key) - break - else: - self._downloader.trouble(u'ERROR: unable to extract video URL') - return - - mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video URL') - return - - video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/') - - # TODO: support choosing qualities - - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - video_title = unescapeHTML(mobj.group('title').decode('utf-8')) - - video_uploader = None - mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage) - if mobj is None: - # lookin for official user - mobj_official = re.search(r'', webpage) - if mobj_official is None: - self._downloader.trouble(u'WARNING: unable to extract uploader nickname') - else: - video_uploader = mobj_official.group(1) - else: - video_uploader = mobj.group(1) - - video_upload_date = None - mobj = re.search(r'
([0-9]{2})-([0-9]{2})-([0-9]{4})
', webpage) - if mobj is not None: - video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1) - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader.decode('utf-8'), - 'upload_date': video_upload_date, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - }] + """Information Extractor for Dailymotion""" + + _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' + IE_NAME = u'dailymotion' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) + + def _real_extract(self, url): + # Extract id and simplified title from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group(1).split('_')[0].split('?')[0] + + video_extension = 'mp4' + + # Retrieve video webpage to extract further information + request = compat_urllib_request.Request(url) + request.add_header('Cookie', 'family_filter=off') + try: + self.report_download_webpage(video_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) + return + + # Extract URL, uploader and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'\s*var flashvars = (.*)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + flashvars = compat_urllib_parse.unquote(mobj.group(1)) + + for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: + if key in flashvars: + max_quality = key + self._downloader.to_screen(u'[dailymotion] Using %s' % key) + break + else: + self._downloader.trouble(u'ERROR: unable to extract video URL') + return + + mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video URL') + return + + video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/') + + # TODO: support choosing qualities + + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = unescapeHTML(mobj.group('title').decode('utf-8')) + + video_uploader = None + mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage) + if mobj is None: + # lookin for official user + mobj_official = re.search(r'', webpage) + if mobj_official is None: + self._downloader.trouble(u'WARNING: unable to extract uploader nickname') + else: + video_uploader = mobj_official.group(1) + else: + video_uploader = mobj.group(1) + + video_upload_date = None + mobj = re.search(r'
([0-9]{2})-([0-9]{2})-([0-9]{4})
', webpage) + if mobj is not None: + video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1) + + return [{ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'upload_date': video_upload_date, + 'title': video_title, + 'ext': video_extension.decode('utf-8'), + }] class GoogleIE(InfoExtractor): - """Information extractor for video.google.com.""" - - _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' - IE_NAME = u'video.google' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id) - - def _real_extract(self, url): - # Extract id from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - video_id = mobj.group(1) - - video_extension = 'mp4' - - # Retrieve video webpage to extract further information - request = compat_urllib_request.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id) - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return - - # Extract URL, uploader, and title from webpage - self.report_extraction(video_id) - mobj = re.search(r"download_url:'([^']+)'", webpage) - if mobj is None: - video_extension = 'flv' - mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - mediaURL = compat_urllib_parse.unquote(mobj.group(1)) - mediaURL = mediaURL.replace('\\x3d', '\x3d') - mediaURL = mediaURL.replace('\\x26', '\x26') - - video_url = mediaURL - - mobj = re.search(r'(.*)', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - video_title = mobj.group(1).decode('utf-8') - - # Extract video description - mobj = re.search(r'([^<]*)', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video description') - return - video_description = mobj.group(1).decode('utf-8') - if not video_description: - video_description = 'No description available.' - - # Extract video thumbnail - if self._downloader.params.get('forcethumbnail', False): - request = compat_urllib_request.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id))) - try: - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video thumbnail') - return - video_thumbnail = mobj.group(1) - else: # we need something to pass to process_info - video_thumbnail = '' - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': None, - 'upload_date': None, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - }] + """Information extractor for video.google.com.""" + + _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' + IE_NAME = u'video.google' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id) + + def _real_extract(self, url): + # Extract id from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + video_extension = 'mp4' + + # Retrieve video webpage to extract further information + request = compat_urllib_request.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id) + try: + self.report_download_webpage(video_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + + # Extract URL, uploader, and title from webpage + self.report_extraction(video_id) + mobj = re.search(r"download_url:'([^']+)'", webpage) + if mobj is None: + video_extension = 'flv' + mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = compat_urllib_parse.unquote(mobj.group(1)) + mediaURL = mediaURL.replace('\\x3d', '\x3d') + mediaURL = mediaURL.replace('\\x26', '\x26') + + video_url = mediaURL + + mobj = re.search(r'(.*)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1).decode('utf-8') + + # Extract video description + mobj = re.search(r'([^<]*)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video description') + return + video_description = mobj.group(1).decode('utf-8') + if not video_description: + video_description = 'No description available.' + + # Extract video thumbnail + if self._downloader.params.get('forcethumbnail', False): + request = compat_urllib_request.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id))) + try: + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1) + else: # we need something to pass to process_info + video_thumbnail = '' + + return [{ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': video_extension.decode('utf-8'), + }] class PhotobucketIE(InfoExtractor): - """Information extractor for photobucket.com.""" - - _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' - IE_NAME = u'photobucket' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) - - def _real_extract(self, url): - # Extract id from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - video_id = mobj.group(1) - - video_extension = 'flv' - - # Retrieve video webpage to extract further information - request = compat_urllib_request.Request(url) - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return - - # Extract URL, uploader, and title from webpage - self.report_extraction(video_id) - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - mediaURL = compat_urllib_parse.unquote(mobj.group(1)) - - video_url = mediaURL - - mobj = re.search(r'(.*) video by (.*) - Photobucket', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') - return - video_title = mobj.group(1).decode('utf-8') - - video_uploader = mobj.group(2).decode('utf-8') - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader, - 'upload_date': None, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - }] + """Information extractor for photobucket.com.""" + + _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' + IE_NAME = u'photobucket' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) + + def _real_extract(self, url): + # Extract id from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + video_extension = 'flv' + + # Retrieve video webpage to extract further information + request = compat_urllib_request.Request(url) + try: + self.report_download_webpage(video_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + + # Extract URL, uploader, and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = compat_urllib_parse.unquote(mobj.group(1)) + + video_url = mediaURL + + mobj = re.search(r'(.*) video by (.*) - Photobucket', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1).decode('utf-8') + + video_uploader = mobj.group(2).decode('utf-8') + + return [{ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader, + 'upload_date': None, + 'title': video_title, + 'ext': video_extension.decode('utf-8'), + }] class YahooIE(InfoExtractor): - """Information extractor for video.yahoo.com.""" - - # _VALID_URL matches all Yahoo! Video URLs - # _VPAGE_URL matches only the extractable '/watch/' URLs - _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' - _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' - IE_NAME = u'video.yahoo' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) - - def _real_extract(self, url, new_video=True): - # Extract ID from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - video_id = mobj.group(2) - video_extension = 'flv' - - # Rewrite valid but non-extractable URLs as - # extractable English language /watch/ URLs - if re.match(self._VPAGE_URL, url) is None: - request = compat_urllib_request.Request(url) - try: - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return - - mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: Unable to extract id field') - return - yahoo_id = mobj.group(1) - - mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: Unable to extract vid field') - return - yahoo_vid = mobj.group(1) - - url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) - return self._real_extract(url, new_video=False) - - # Retrieve video webpage to extract further information - request = compat_urllib_request.Request(url) - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return - - # Extract uploader and title from webpage - self.report_extraction(video_id) - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = mobj.group(1).decode('utf-8') - - mobj = re.search(r'

(.*)

', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video uploader') - return - video_uploader = mobj.group(1).decode('utf-8') - - # Extract video thumbnail - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video thumbnail') - return - video_thumbnail = mobj.group(1).decode('utf-8') - - # Extract video description - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video description') - return - video_description = mobj.group(1).decode('utf-8') - if not video_description: - video_description = 'No description available.' - - # Extract video height and width - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video height') - return - yv_video_height = mobj.group(1) - - mobj = re.search(r'', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video width') - return - yv_video_width = mobj.group(1) - - # Retrieve video playlist to extract media URL - # I'm not completely sure what all these options are, but we - # seem to need most of them, otherwise the server sends a 401. - yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents - yv_bitrate = '700' # according to Wikipedia this is hard-coded - request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + - '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + - '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return - - # Extract media URL from playlist XML - mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + + mobj = re.search(r'

(.*)

', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video uploader') + return + video_uploader = mobj.group(1).decode('utf-8') + + # Extract video thumbnail + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1).decode('utf-8') + + # Extract video description + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video description') + return + video_description = mobj.group(1).decode('utf-8') + if not video_description: + video_description = 'No description available.' + + # Extract video height and width + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video height') + return + yv_video_height = mobj.group(1) + + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video width') + return + yv_video_width = mobj.group(1) + + # Retrieve video playlist to extract media URL + # I'm not completely sure what all these options are, but we + # seem to need most of them, otherwise the server sends a 401. + yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents + yv_bitrate = '700' # according to Wikipedia this is hard-coded + request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + + '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + + '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') + try: + self.report_download_webpage(video_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + + # Extract media URL from playlist XML + mobj = re.search(r'[^:]*: (.*?)( \([^\(]*\))?
', webpage) - if mobj is not None: - video_upload_date = mobj.group(1) - - # Vimeo specific: extract request signature and timestamp - sig = config['request']['signature'] - timestamp = config['request']['timestamp'] - - # Vimeo specific: extract video codec and quality information - # First consider quality, then codecs, then take everything - # TODO bind to format param - codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')] - files = { 'hd': [], 'sd': [], 'other': []} - for codec_name, codec_extension in codecs: - if codec_name in config["video"]["files"]: - if 'hd' in config["video"]["files"][codec_name]: - files['hd'].append((codec_name, codec_extension, 'hd')) - elif 'sd' in config["video"]["files"][codec_name]: - files['sd'].append((codec_name, codec_extension, 'sd')) - else: - files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0])) - - for quality in ('hd', 'sd', 'other'): - if len(files[quality]) > 0: - video_quality = files[quality][0][2] - video_codec = files[quality][0][0] - video_extension = files[quality][0][1] - self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) - break - else: - self._downloader.trouble(u'ERROR: no known codec found') - return - - video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ - %(video_id, sig, timestamp, video_quality, video_codec.upper()) - - return [{ - 'id': video_id, - 'url': video_url, - 'uploader': video_uploader, - 'upload_date': video_upload_date, - 'title': video_title, - 'ext': video_extension, - 'thumbnail': video_thumbnail, - 'description': video_description, - }] + """Information extractor for vimeo.com.""" + + # _VALID_URL matches Vimeo URLs + _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)' + IE_NAME = u'vimeo' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id) + + def _real_extract(self, url, new_video=True): + # Extract ID from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + video_id = mobj.group(1) + + # Retrieve video webpage to extract further information + request = compat_urllib_request.Request(url, None, std_headers) + try: + self.report_download_webpage(video_id) + webpage = compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) + return + + # Now we begin extracting as much information as we can from what we + # retrieved. First we extract the information common to all extractors, + # and latter we extract those that are Vimeo specific. + self.report_extraction(video_id) + + # Extract the config JSON + config = webpage.split(' = {config:')[1].split(',assets:')[0] + try: + config = json.loads(config) + except: + self._downloader.trouble(u'ERROR: unable to extract info section') + return + + # Extract title + video_title = config["video"]["title"] + + # Extract uploader + video_uploader = config["video"]["owner"]["name"] + + # Extract video thumbnail + video_thumbnail = config["video"]["thumbnail"] + + # Extract video description + video_description = get_element_by_id("description", webpage.decode('utf8')) + if video_description: video_description = clean_html(video_description) + else: video_description = '' + + # Extract upload date + video_upload_date = None + mobj = re.search(r'', webpage) + if mobj is not None: + video_upload_date = mobj.group(1) + + # Vimeo specific: extract request signature and timestamp + sig = config['request']['signature'] + timestamp = config['request']['timestamp'] + + # Vimeo specific: extract video codec and quality information + # First consider quality, then codecs, then take everything + # TODO bind to format param + codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')] + files = { 'hd': [], 'sd': [], 'other': []} + for codec_name, codec_extension in codecs: + if codec_name in config["video"]["files"]: + if 'hd' in config["video"]["files"][codec_name]: + files['hd'].append((codec_name, codec_extension, 'hd')) + elif 'sd' in config["video"]["files"][codec_name]: + files['sd'].append((codec_name, codec_extension, 'sd')) + else: + files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0])) + + for quality in ('hd', 'sd', 'other'): + if len(files[quality]) > 0: + video_quality = files[quality][0][2] + video_codec = files[quality][0][0] + video_extension = files[quality][0][1] + self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) + break + else: + self._downloader.trouble(u'ERROR: no known codec found') + return + + video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ + %(video_id, sig, timestamp, video_quality, video_codec.upper()) + + return [{ + 'id': video_id, + 'url': video_url, + 'uploader': video_uploader, + 'upload_date': video_upload_date, + 'title': video_title, + 'ext': video_extension, + 'thumbnail': video_thumbnail, + 'description': video_description, + }] class ArteTvIE(InfoExtractor): - """arte.tv information extractor.""" - - _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' - _LIVE_URL = r'index-[0-9]+\.html$' - - IE_NAME = u'arte.tv' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id) - - def fetch_webpage(self, url): - self._downloader.increment_downloads() - request = compat_urllib_request.Request(url) - try: - self.report_download_webpage(url) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return - except ValueError as err: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - return webpage - - def grep_webpage(self, url, regex, regexFlags, matchTuples): - page = self.fetch_webpage(url) - mobj = re.search(regex, page, regexFlags) - info = {} - - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - for (i, key, err) in matchTuples: - if mobj.group(i) is None: - self._downloader.trouble(err) - return - else: - info[key] = mobj.group(i) - - return info - - def extractLiveStream(self, url): - video_lang = url.split('/')[-4] - info = self.grep_webpage( - url, - r'src="(.*?/videothek_js.*?\.js)', - 0, - [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) - ] - ) - http_host = url.split('/')[2] - next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url'))) - info = self.grep_webpage( - next_url, - r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' + - '(http://.*?\.swf).*?' + - '(rtmp://.*?)\'', - re.DOTALL, - [ - (1, 'path', u'ERROR: could not extract video path: %s' % url), - (2, 'player', u'ERROR: could not extract video player: %s' % url), - (3, 'url', u'ERROR: could not extract video url: %s' % url) - ] - ) - video_url = u'%s/%s' % (info.get('url'), info.get('path')) - - def extractPlus7Stream(self, url): - video_lang = url.split('/')[-3] - info = self.grep_webpage( - url, - r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', - 0, - [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) - ] - ) - next_url = compat_urllib_parse.unquote(info.get('url')) - info = self.grep_webpage( - next_url, - r'