diff options
Diffstat (limited to 'youtube_dl')
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 3 | ||||
| -rw-r--r-- | youtube_dl/extractor/alphaporno.py | 77 | ||||
| -rw-r--r-- | youtube_dl/extractor/archiveorg.py | 52 | ||||
| -rw-r--r-- | youtube_dl/extractor/arte.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/bbccouk.py | 95 | ||||
| -rw-r--r-- | youtube_dl/extractor/cnn.py | 31 | ||||
| -rw-r--r-- | youtube_dl/extractor/eroprofile.py | 45 | ||||
| -rw-r--r-- | youtube_dl/extractor/sunporno.py | 18 |
8 files changed, 263 insertions, 62 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index c8a77616e..c79e5b7d0 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -7,6 +7,7 @@ from .adobetv import AdobeTVIE from .adultswim import AdultSwimIE from .aftonbladet import AftonbladetIE from .aljazeera import AlJazeeraIE +from .alphaporno import AlphaPornoIE from .anitube import AnitubeIE from .anysex import AnySexIE from .aol import AolIE @@ -64,6 +65,7 @@ from .cnet import CNETIE from .cnn import ( CNNIE, CNNBlogsIE, + CNNArticleIE, ) from .collegehumor import CollegeHumorIE from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE @@ -108,6 +110,7 @@ from .elpais import ElPaisIE from .empflix import EMPFlixIE from .engadget import EngadgetIE from .eporner import EpornerIE +from .eroprofile import EroProfileIE from .escapist import EscapistIE from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE diff --git a/youtube_dl/extractor/alphaporno.py b/youtube_dl/extractor/alphaporno.py new file mode 100644 index 000000000..c34719d1f --- /dev/null +++ b/youtube_dl/extractor/alphaporno.py @@ -0,0 +1,77 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + parse_duration, + parse_filesize, + int_or_none, +) + + +class AlphaPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)' + _TEST = { + 'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/', + 'md5': 'feb6d3bba8848cd54467a87ad34bd38e', + 'info_dict': { + 'id': '258807', + 'display_id': 'sensual-striptease-porn-with-samantha-alexandra', + 'ext': 'mp4', + 'title': 'Sensual striptease porn with Samantha Alexandra', + 'thumbnail': 're:https?://.*\.jpg$', + 'timestamp': 1418694611, + 'upload_date': '20141216', + 'duration': 387, + 'filesize_approx': 54120000, + 'tbr': 1145, + 'categories': list, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None) + + video_url = self._search_regex( + r"video_url\s*:\s*'([^']+)'", webpage, 'video url') + ext = self._html_search_meta( + 'encodingFormat', webpage, 'ext', default='.mp4')[1:] + + title = self._search_regex( + [r'<meta content="([^"]+)" itemprop="description">', + r'class="title" itemprop="name">([^<]+)<'], + webpage, 'title') + thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail') + timestamp = parse_iso8601(self._html_search_meta( + 'uploadDate', webpage, 'upload date')) + duration = parse_duration(self._html_search_meta( + 'duration', webpage, 'duration')) + filesize_approx = parse_filesize(self._html_search_meta( + 'contentSize', webpage, 'file size')) + bitrate = int_or_none(self._html_search_meta( + 'bitrate', webpage, 'bitrate')) + categories = self._html_search_meta( + 'keywords', webpage, 'categories', default='').split(',') + + age_limit = self._rta_search(webpage) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'ext': ext, + 'title': title, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'filesize_approx': filesize_approx, + 'tbr': bitrate, + 'categories': categories, + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py index 34ce8429b..9fc35a42b 100644 --- a/youtube_dl/extractor/archiveorg.py +++ b/youtube_dl/extractor/archiveorg.py @@ -1,42 +1,48 @@ from __future__ import unicode_literals -import json -import re - from .common import InfoExtractor -from ..utils import ( - unified_strdate, -) +from ..utils import unified_strdate class ArchiveOrgIE(InfoExtractor): IE_NAME = 'archive.org' IE_DESC = 'archive.org videos' - _VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$' - _TEST = { - "url": "http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect", - 'file': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv', + _VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$' + _TESTS = [{ + 'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect', 'md5': '8af1d4cf447933ed3c7f4871162602db', 'info_dict': { - "title": "1968 Demo - FJCC Conference Presentation Reel #1", - "description": "Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>", - "upload_date": "19681210", - "uploader": "SRI International" + 'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect', + 'ext': 'ogv', + 'title': '1968 Demo - FJCC Conference Presentation Reel #1', + 'description': 'md5:1780b464abaca9991d8968c877bb53ed', + 'upload_date': '19681210', + 'uploader': 'SRI International' + } + }, { + 'url': 'https://archive.org/details/Cops1922', + 'md5': '18f2a19e6d89af8425671da1cf3d4e04', + 'info_dict': { + 'id': 'Cops1922', + 'ext': 'ogv', + 'title': 'Buster Keaton\'s "Cops" (1922)', + 'description': 'md5:70f72ee70882f713d4578725461ffcc3', } - } + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) json_url = url + ('?' if '?' in url else '&') + 'output=json' - json_data = self._download_webpage(json_url, video_id) - data = json.loads(json_data) + data = self._download_json(json_url, video_id) + + def get_optional(data_dict, field): + return data_dict['metadata'].get(field, [None])[0] - title = data['metadata']['title'][0] - description = data['metadata']['description'][0] - uploader = data['metadata']['creator'][0] - upload_date = unified_strdate(data['metadata']['date'][0]) + title = get_optional(data, 'title') + description = get_optional(data, 'description') + uploader = get_optional(data, 'creator') + upload_date = unified_strdate(get_optional(data, 'date')) formats = [ { diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 219631b9b..929dd3cc5 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -37,7 +37,7 @@ class ArteTvIE(InfoExtractor): config_xml_url, video_id, note='Downloading configuration') formats = [{ - 'forma_id': q.attrib['quality'], + 'format_id': q.attrib['quality'], # The playpath starts at 'mp4:', if we don't manually # split the url, rtmpdump will incorrectly parse them 'url': q.text.split('mp4:', 1)[0], @@ -133,7 +133,7 @@ class ArteTVPlus7IE(InfoExtractor): 'width': int_or_none(f.get('width')), 'height': int_or_none(f.get('height')), 'tbr': int_or_none(f.get('bitrate')), - 'quality': qfunc(f['quality']), + 'quality': qfunc(f.get('quality')), 'source_preference': source_pref, } diff --git a/youtube_dl/extractor/bbccouk.py b/youtube_dl/extractor/bbccouk.py index 2d2f742ae..f690dc803 100644 --- a/youtube_dl/extractor/bbccouk.py +++ b/youtube_dl/extractor/bbccouk.py @@ -71,7 +71,20 @@ class BBCCoUkIE(SubtitlesInfoExtractor): 'skip_download': True, }, 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', - }, + }, { + 'url': 'http://www.bbc.co.uk/programmes/b04v20dw', + 'info_dict': { + 'id': 'b04v209v', + 'ext': 'flv', + 'title': 'Pete Tong, The Essential New Tune Special', + 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!", + 'duration': 10800, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + } ] def _extract_asx_playlist(self, connection, programme_id): @@ -203,6 +216,59 @@ class BBCCoUkIE(SubtitlesInfoExtractor): return formats, subtitles + def _download_playlist(self, playlist_id): + try: + playlist = self._download_json( + 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id, + playlist_id, 'Downloading playlist JSON') + + version = playlist.get('defaultAvailableVersion') + if version: + smp_config = version['smpConfig'] + title = smp_config['title'] + description = smp_config['summary'] + for item in smp_config['items']: + kind = item['kind'] + if kind != 'programme' and kind != 'radioProgramme': + continue + programme_id = item.get('vpid') + duration = int(item.get('duration')) + formats, subtitles = self._download_media_selector(programme_id) + return programme_id, title, description, duration, formats, subtitles + except ExtractorError as ee: + if not isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404: + raise + + # fallback to legacy playlist + playlist = self._download_xml( + 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, + playlist_id, 'Downloading legacy playlist XML') + + no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') + if no_items is not None: + reason = no_items.get('reason') + if reason == 'preAvailability': + msg = 'Episode %s is not yet available' % playlist_id + elif reason == 'postAvailability': + msg = 'Episode %s is no longer available' % playlist_id + elif reason == 'noMedia': + msg = 'Episode %s is not currently available' % playlist_id + else: + msg = 'Episode %s is not available: %s' % (playlist_id, reason) + raise ExtractorError(msg, expected=True) + + for item in self._extract_items(playlist): + kind = item.get('kind') + if kind != 'programme' and kind != 'radioProgramme': + continue + title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text + description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text + programme_id = item.get('identifier') + duration = int(item.get('duration')) + formats, subtitles = self._download_media_selector(programme_id) + + return programme_id, title, description, duration, formats, subtitles + def _real_extract(self, url): group_id = self._match_id(url) @@ -219,32 +285,7 @@ class BBCCoUkIE(SubtitlesInfoExtractor): duration = player['duration'] formats, subtitles = self._download_media_selector(programme_id) else: - playlist = self._download_xml( - 'http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, - group_id, 'Downloading playlist XML') - - no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') - if no_items is not None: - reason = no_items.get('reason') - if reason == 'preAvailability': - msg = 'Episode %s is not yet available' % group_id - elif reason == 'postAvailability': - msg = 'Episode %s is no longer available' % group_id - elif reason == 'noMedia': - msg = 'Episode %s is not currently available' % group_id - else: - msg = 'Episode %s is not available: %s' % (group_id, reason) - raise ExtractorError(msg, expected=True) - - for item in self._extract_items(playlist): - kind = item.get('kind') - if kind != 'programme' and kind != 'radioProgramme': - continue - title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text - description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text - programme_id = item.get('identifier') - duration = int(item.get('duration')) - formats, subtitles = self._download_media_selector(programme_id) + programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) if self._downloader.params.get('listsubtitles', False): self._list_available_subtitles(programme_id, subtitles) diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index 81142ee41..1bff005d6 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -11,14 +11,14 @@ from ..utils import ( class CNNIE(InfoExtractor): - _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/ - (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn(-ap)?|(?=&)))''' + _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/ + (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn(?:-ap)?|(?=&)))''' _TESTS = [{ 'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', 'md5': '3e6121ea48df7e2259fe73a0628605c4', 'info_dict': { - 'id': 'sports_2013_06_09_nadal-1-on-1.cnn', + 'id': 'sports/2013/06/09/nadal-1-on-1.cnn', 'ext': 'mp4', 'title': 'Nadal wins 8th French Open title', 'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.', @@ -127,3 +127,28 @@ class CNNBlogsIE(InfoExtractor): 'url': cnn_url, 'ie_key': CNNIE.ie_key(), } + + +class CNNArticleIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)' + _TEST = { + 'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/', + 'md5': '275b326f85d80dff7592a9820f5dc887', + 'info_dict': { + 'id': 'bestoftv/2014/12/21/sotu-crowley-president-obama-north-korea-not-going-to-be-intimidated.cnn', + 'ext': 'mp4', + 'title': 'Obama: We\'re not going to be intimidated', + 'description': 'md5:e735586f3dc936075fa654a4d91b21f9', + 'upload_date': '20141220', + }, + 'add_ie': ['CNN'], + } + + def _real_extract(self, url): + webpage = self._download_webpage(url, url_basename(url)) + cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url') + return { + '_type': 'url', + 'url': 'http://cnn.com/video/?/video/' + cnn_url, + 'ie_key': CNNIE.ie_key(), + } diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py new file mode 100644 index 000000000..79e2fbd39 --- /dev/null +++ b/youtube_dl/extractor/eroprofile.py @@ -0,0 +1,45 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class EroProfileIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)' + _TEST = { + 'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore', + 'md5': 'c26f351332edf23e1ea28ce9ec9de32f', + 'info_dict': { + 'id': '3733775', + 'display_id': 'sexy-babe-softcore', + 'ext': 'm4v', + 'title': 'sexy babe softcore', + 'thumbnail': 're:https?://.*\.jpg', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'], + webpage, 'video id', default=None) + + video_url = self._search_regex( + r'<source src="([^"]+)', webpage, 'video url') + title = self._html_search_regex( + r'Title:</th><td>([^<]+)</td>', webpage, 'title') + thumbnail = self._search_regex( + r'onclick="showVideoPlayer\(\)"><img src="([^"]+)', + webpage, 'thumbnail', fatal=False) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py index 263f09b46..8a333f1d2 100644 --- a/youtube_dl/extractor/sunporno.py +++ b/youtube_dl/extractor/sunporno.py @@ -28,23 +28,27 @@ class SunPornoIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title') - description = self._html_search_meta('description', webpage, 'description') + title = self._html_search_regex( + r'<title>([^<]+)</title>', webpage, 'title') + description = self._html_search_meta( + 'description', webpage, 'description') thumbnail = self._html_search_regex( r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) duration = parse_duration(self._search_regex( - r'Duration:\s*(\d+:\d+)\s*<', webpage, 'duration', fatal=False)) + r'itemprop="duration">\s*(\d+:\d+)\s*<', + webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex( - r'class="views">\s*(\d+)\s*<', webpage, 'view count', fatal=False)) + r'class="views">\s*(\d+)\s*<', + webpage, 'view count', fatal=False)) comment_count = int_or_none(self._html_search_regex( - r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False)) + r'(\d+)</b> Comments?', + webpage, 'comment count', fatal=False)) formats = [] quality = qualities(['mp4', 'flv']) |