From d96680f58d918c99baab952338f547c42266bdf3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sun, 5 May 2013 13:07:00 +0200 Subject: [PATCH] PhotobucketIE: accept new format of urls and add a test --- test/tests.json | 9 +++++++++ youtube_dl/InfoExtractors.py | 31 ++++++++++++++++++++++--------- 2 files changed, 31 insertions(+), 9 deletions(-) diff --git a/test/tests.json b/test/tests.json index b4d511dd8..66e93a33a 100644 --- a/test/tests.json +++ b/test/tests.json @@ -411,5 +411,14 @@ "info_dict":{ "title":"Sucked on a toilet" } + }, + { + "name": "Photobucket", + "url": "http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0", + "file": "zpsc0c3b9fa.mp4", + "md5": "7dabfb92b0a31f6c16cebc0f8e60ff99", + "info_dict":{ + "title":"Tired of Link Building? Try BacklinkMyDomain.com!" + } } ] diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 8c3751d0a..a98d403b3 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -848,7 +848,10 @@ class DailymotionIE(InfoExtractor): class PhotobucketIE(InfoExtractor): """Information extractor for photobucket.com.""" - _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' + # TODO: the original _VALID_URL was: + # r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' + # Check if it's necessary to keep the old extracion process + _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P.*)\.(?P(flv)|(mp4))' IE_NAME = u'photobucket' def _real_extract(self, url): @@ -857,20 +860,30 @@ class PhotobucketIE(InfoExtractor): if mobj is None: raise ExtractorError(u'Invalid URL: %s' % url) - video_id = mobj.group(1) + video_id = mobj.group('id') - video_extension = 'flv' + video_extension = mobj.group('ext') # 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: - raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err)) + webpage = self._download_webpage(url, video_id) # Extract URL, uploader, and title from webpage self.report_extraction(video_id) + # We try first by looking the javascript code: + mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P.*?)\);', webpage) + if mobj is not None: + info = json.loads(mobj.group('json')) + return [{ + 'id': video_id, + 'url': info[u'downloadUrl'], + 'uploader': info[u'username'], + 'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'), + 'title': info[u'title'], + 'ext': video_extension, + 'thumbnail': info[u'thumbUrl'], + }] + + # We try looking in other parts of the webpage mobj = re.search(r'', webpage) if mobj is None: raise ExtractorError(u'Unable to extract media URL')