From a229909fa616c8b2820ea3b254861f07bedcd376 Mon Sep 17 00:00:00 2001 From: Naglis Jonaitis Date: Sun, 3 Aug 2014 21:24:44 +0300 Subject: [PATCH 1/7] [jove] Add new extractor. Closes #3177 --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/jove.py | 64 ++++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+) create mode 100644 youtube_dl/extractor/jove.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 2bf8bc5e8..c80a1bd48 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -144,6 +144,7 @@ from .ivi import ( from .izlesene import IzleseneIE from .jadorecettepub import JadoreCettePubIE from .jeuxvideo import JeuxVideoIE +from .jove import JoveIE from .jukebox import JukeboxIE from .justintv import JustinTVIE from .jpopsukitv import JpopsukiIE diff --git a/youtube_dl/extractor/jove.py b/youtube_dl/extractor/jove.py new file mode 100644 index 000000000..a7110b683 --- /dev/null +++ b/youtube_dl/extractor/jove.py @@ -0,0 +1,64 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +from datetime import datetime + +from .common import InfoExtractor +from ..utils import determine_ext, ExtractorError + + +class JoveIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P[0-9]+)' + _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}' + _TEST = { + 'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current', + 'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b', + 'info_dict': { + 'id': '2744', + 'ext': 'mp4', + 'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation', + 'description': 'Transcranial direct current stimulation (tDCS) is an established technique to modulate cortical excitability1,2. It has been ...', + 'thumbnail': 're:^https?://.*\.png$', + 'upload_date': '20110523', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._html_search_meta('citation_title', webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._html_search_meta( + 'description', webpage, 'description', fatal=False) + publish_date = self._html_search_meta( + 'citation_publication_date', webpage, 'publish date', fatal=False) + if publish_date: + publish_date = datetime.strptime(publish_date, + '%Y/%m/%d').strftime('%Y%m%d') + + # Not the same as video_id. + chapters_id = self._html_search_regex( + r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id') + chapters_xml = self._download_xml( + self._CHAPTERS_URL.format(video_id=chapters_id), + video_id, note='Downloading chapter XML', + errnote='Failed to download chapter XML' + ) + video_url = chapters_xml.attrib.get('video') + if not video_url: + raise ExtractorError('Failed to get the video URL') + + ext = determine_ext(video_url) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'ext': ext, + 'thumbnail': thumbnail, + 'description': description, + 'upload_date': publish_date, + } From c1d293cfa68031e0ec1a4190041f280d22c2b026 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Aug 2014 02:07:04 +0700 Subject: [PATCH 2/7] [dfb] Fix f4m manifest URL --- youtube_dl/extractor/dfb.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/dfb.py b/youtube_dl/extractor/dfb.py index cb8e06822..8049779b0 100644 --- a/youtube_dl/extractor/dfb.py +++ b/youtube_dl/extractor/dfb.py @@ -30,7 +30,7 @@ class DFBIE(InfoExtractor): video_id) video_info = player_info.find('video') - f4m_info = self._download_xml(video_info.find('url').text, video_id) + f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id) token_el = f4m_info.find('token') manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0' From 4d9bd478f9d846291c722da002266504fce824ba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 18 Aug 2014 19:20:53 +0700 Subject: [PATCH 3/7] [pbs] Extract coveplayerid (Closes #3522) --- youtube_dl/extractor/pbs.py | 42 +++++++++++++++++++++++++------------ 1 file changed, 29 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index ec95d0704..09bee6561 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -20,17 +20,30 @@ class PBSIE(InfoExtractor): ) ''' - _TEST = { - 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', - 'md5': 'ce1888486f0908d555a8093cac9a7362', - 'info_dict': { - 'id': '2365006249', - 'ext': 'mp4', - 'title': 'A More Perfect Union', - 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', - 'duration': 3190, + _TESTS = [ + { + 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', + 'md5': 'ce1888486f0908d555a8093cac9a7362', + 'info_dict': { + 'id': '2365006249', + 'ext': 'mp4', + 'title': 'A More Perfect Union', + 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', + 'duration': 3190, + }, + }, + { + 'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/', + 'md5': 'b19856d7f5351b17a5ab1dc6a64be633', + 'info_dict': { + 'id': '2201174722', + 'ext': 'mp4', + 'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist', + 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28', + 'duration': 801, + }, }, - } + ] def _extract_ids(self, url): mobj = re.match(self._VALID_URL, url) @@ -40,10 +53,13 @@ class PBSIE(InfoExtractor): if presumptive_id: webpage = self._download_webpage(url, display_id) - # frontline video embed + MEDIA_ID_REGEXES = [ + r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed + r'class="coveplayerid">([^<]+)<', # coveplayer + ] + media_id = self._search_regex( - r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", - webpage, 'frontline video ID', fatal=False, default=None) + MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None) if media_id: return media_id, presumptive_id From cd6b48365e29400044b8852226bed41490ef6e2f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 18 Aug 2014 19:24:18 +0700 Subject: [PATCH 4/7] [pbs] Add frontline video test --- youtube_dl/extractor/pbs.py | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 09bee6561..dee4af6f1 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -32,6 +32,17 @@ class PBSIE(InfoExtractor): 'duration': 3190, }, }, + { + 'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/', + 'md5': '143c98aa54a346738a3d78f54c925321', + 'info_dict': { + 'id': '2365297690', + 'ext': 'mp4', + 'title': 'Losing Iraq', + 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e', + 'duration': 5050, + }, + }, { 'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/', 'md5': 'b19856d7f5351b17a5ab1dc6a64be633', From 6493f5d7045c90b2a6820b2cda58553d3a2fce8f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Mon, 18 Aug 2014 15:39:35 +0200 Subject: [PATCH 5/7] [rtlnl] Add extractor for rtlxl.nl (closes #3523) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/rtlnl.py | 52 ++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) create mode 100644 youtube_dl/extractor/rtlnl.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 27602e0c0..d6056ce8d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -252,6 +252,7 @@ from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE +from .rtlnl import RtlXlIE from .rtlnow import RTLnowIE from .rts import RTSIE from .rtve import RTVEALaCartaIE diff --git a/youtube_dl/extractor/rtlnl.py b/youtube_dl/extractor/rtlnl.py new file mode 100644 index 000000000..14928cd62 --- /dev/null +++ b/youtube_dl/extractor/rtlnl.py @@ -0,0 +1,52 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class RtlXlIE(InfoExtractor): + IE_NAME = 'rtlxl.nl' + _VALID_URL = r'https?://www\.rtlxl\.nl/#!/[^/]+/(?P[^/?]+)' + + _TEST = { + 'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677', + 'info_dict': { + 'id': '6e4203a6-0a5e-3596-8424-c599a59e0677', + 'ext': 'flv', + 'title': 'RTL Nieuws - Laat', + 'description': 'Dagelijks het laatste nieuws uit binnen- en ' + 'buitenland. Voor nog meer nieuws kunt u ook gebruikmaken van ' + 'onze mobiele apps.', + 'timestamp': 1408051800, + 'upload_date': '20140814', + }, + 'params': { + # We download the first bytes of the first fragment, it can't be + # processed by the f4m downloader beacuse it isn't complete + 'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + uuid = mobj.group('uuid') + + info = self._download_json( + 'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid, + uuid) + meta = info['meta'] + material = info['material'][0] + episode_info = info['episodes'][0] + + f4m_url = 'http://manifest.us.rtl.nl' + material['videopath'] + progname = info['abstracts'][0]['name'] + subtitle = material['title'] or info['episodes'][0]['name'] + + return { + 'id': uuid, + 'title': '%s - %s' % (progname, subtitle), + 'formats': self._extract_f4m_formats(f4m_url, uuid), + 'timestamp': material['original_date'], + 'description': episode_info['synopsis'], + } From 938dd254e557612b8a6e1f0a2dd1689fca30b9ed Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Mon, 18 Aug 2014 22:43:35 +0200 Subject: [PATCH 6/7] [mitele] Add extractor for mitele.es --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/mitele.py | 60 ++++++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+) create mode 100644 youtube_dl/extractor/mitele.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d6056ce8d..6780f7f99 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -178,6 +178,7 @@ from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mit import TechTVMITIE, MITIE, OCWMITIE +from .mitele import MiTeleIE from .mixcloud import MixcloudIE from .mlb import MLBIE from .mpora import MporaIE diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py new file mode 100644 index 000000000..979f3d692 --- /dev/null +++ b/youtube_dl/extractor/mitele.py @@ -0,0 +1,60 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + get_element_by_attribute, + parse_duration, + strip_jsonp, +) + + +class MiTeleIE(InfoExtractor): + IE_NAME = 'mitele.es' + _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P[^/]+)/' + + _TEST = { + 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', + 'md5': '6a75fe9d0d3275bead0cb683c616fddb', + 'info_dict': { + 'id': '0fce117d', + 'ext': 'mp4', + 'title': 'Programa 144 - Tor, la web invisible', + 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f', + 'display_id': 'programa-144', + 'duration': 2913, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + episode = mobj.group('episode') + webpage = self._download_webpage(url, episode) + embed_data_json = self._search_regex( + r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', + flags=re.DOTALL + ).replace('\'', '"') + embed_data = json.loads(embed_data_json) + + info_url = embed_data['flashvars']['host'] + info_el = self._download_xml(info_url, episode).find('./video/info') + + video_link = info_el.find('videoUrl/link').text + token_query = compat_urllib_parse.urlencode({'id': video_link}) + token_info = self._download_json( + 'http://token.mitele.es/?' + token_query, episode, + transform_source=strip_jsonp + ) + + return { + 'id': embed_data['videoId'], + 'display_id': episode, + 'title': info_el.find('title').text, + 'url': token_info['tokenizedUrl'], + 'description': get_element_by_attribute('class', 'text', webpage), + 'thumbnail': info_el.find('thumb').text, + 'duration': parse_duration(info_el.find('duration').text), + } From fe556f1b0cfd5782ec379a731f4b8879f2a352a3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 19 Aug 2014 20:02:08 +0700 Subject: [PATCH 7/7] [jove] Simplify, extract full description and add test for video that requires subscription --- youtube_dl/extractor/jove.py | 76 ++++++++++++++++++++++-------------- youtube_dl/utils.py | 1 + 2 files changed, 47 insertions(+), 30 deletions(-) diff --git a/youtube_dl/extractor/jove.py b/youtube_dl/extractor/jove.py index a7110b683..cf73cd753 100644 --- a/youtube_dl/extractor/jove.py +++ b/youtube_dl/extractor/jove.py @@ -1,64 +1,80 @@ -# coding: utf-8 from __future__ import unicode_literals import re -from datetime import datetime from .common import InfoExtractor -from ..utils import determine_ext, ExtractorError +from ..utils import ( + ExtractorError, + unified_strdate +) class JoveIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P[0-9]+)' _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}' - _TEST = { - 'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current', - 'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b', - 'info_dict': { - 'id': '2744', - 'ext': 'mp4', - 'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation', - 'description': 'Transcranial direct current stimulation (tDCS) is an established technique to modulate cortical excitability1,2. It has been ...', - 'thumbnail': 're:^https?://.*\.png$', - 'upload_date': '20110523', - } - } + _TESTS = [ + { + 'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current', + 'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b', + 'info_dict': { + 'id': '2744', + 'ext': 'mp4', + 'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation', + 'description': 'md5:015dd4509649c0908bc27f049e0262c6', + 'thumbnail': 're:^https?://.*\.png$', + 'upload_date': '20110523', + } + }, + { + 'url': 'http://www.jove.com/video/51796/culturing-caenorhabditis-elegans-axenic-liquid-media-creation', + 'md5': '914aeb356f416811d911996434811beb', + 'info_dict': { + 'id': '51796', + 'ext': 'mp4', + 'title': 'Culturing Caenorhabditis elegans in Axenic Liquid Media and Creation of Transgenic Worms by Microparticle Bombardment', + 'description': 'md5:35ff029261900583970c4023b70f1dc9', + 'thumbnail': 're:^https?://.*\.png$', + 'upload_date': '20140802', + } + }, + + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - title = self._html_search_meta('citation_title', webpage, 'title') - thumbnail = self._og_search_thumbnail(webpage) - description = self._html_search_meta( - 'description', webpage, 'description', fatal=False) - publish_date = self._html_search_meta( - 'citation_publication_date', webpage, 'publish date', fatal=False) - if publish_date: - publish_date = datetime.strptime(publish_date, - '%Y/%m/%d').strftime('%Y%m%d') - # Not the same as video_id. chapters_id = self._html_search_regex( r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id') + chapters_xml = self._download_xml( self._CHAPTERS_URL.format(video_id=chapters_id), - video_id, note='Downloading chapter XML', - errnote='Failed to download chapter XML' - ) + video_id, note='Downloading chapters XML', + errnote='Failed to download chapters XML') + video_url = chapters_xml.attrib.get('video') if not video_url: raise ExtractorError('Failed to get the video URL') - ext = determine_ext(video_url) + title = self._html_search_meta('citation_title', webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._html_search_regex( + r'

(.+?)

', + webpage, 'description', fatal=False) + publish_date = unified_strdate(self._html_search_meta( + 'citation_publication_date', webpage, 'publish date', fatal=False)) + comment_count = self._html_search_regex( + r'