You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

126 lines
4.4 KiB

Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
  1. from __future__ import unicode_literals
  2. import re
  3. from .common import InfoExtractor
  4. from ..utils import (
  5. ExtractorError,
  6. int_or_none,
  7. float_or_none,
  8. unescapeHTML,
  9. )
  10. class WistiaIE(InfoExtractor):
  11. _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]+)'
  12. _API_URL = 'http://fast.wistia.com/embed/medias/%s.json'
  13. _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s'
  14. _TESTS = [{
  15. 'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
  16. 'md5': 'cafeb56ec0c53c18c97405eecb3133df',
  17. 'info_dict': {
  18. 'id': 'sh7fpupwlt',
  19. 'ext': 'mov',
  20. 'title': 'Being Resourceful',
  21. 'description': 'a Clients From Hell Video Series video from worldwidewebhosting',
  22. 'upload_date': '20131204',
  23. 'timestamp': 1386185018,
  24. 'duration': 117,
  25. },
  26. }, {
  27. 'url': 'wistia:sh7fpupwlt',
  28. 'only_matching': True,
  29. }, {
  30. # with hls video
  31. 'url': 'wistia:807fafadvk',
  32. 'only_matching': True,
  33. }, {
  34. 'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt',
  35. 'only_matching': True,
  36. }, {
  37. 'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json',
  38. 'only_matching': True,
  39. }]
  40. @staticmethod
  41. def _extract_url(webpage):
  42. match = re.search(
  43. r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage)
  44. if match:
  45. return unescapeHTML(match.group('url'))
  46. match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
  47. if match:
  48. return 'wistia:%s' % match.group('id')
  49. match = re.search(
  50. r'''(?sx)
  51. <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
  52. <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
  53. ''', webpage)
  54. if match:
  55. return 'wistia:%s' % match.group('id')
  56. def _real_extract(self, url):
  57. video_id = self._match_id(url)
  58. data_json = self._download_json(
  59. self._API_URL % video_id, video_id,
  60. # Some videos require this.
  61. headers={
  62. 'Referer': url if url.startswith('http') else self._IFRAME_URL % video_id,
  63. })
  64. if data_json.get('error'):
  65. raise ExtractorError(
  66. 'Error while getting the playlist', expected=True)
  67. data = data_json['media']
  68. title = data['name']
  69. formats = []
  70. thumbnails = []
  71. for a in data['assets']:
  72. aurl = a.get('url')
  73. if not aurl:
  74. continue
  75. astatus = a.get('status')
  76. atype = a.get('type')
  77. if (astatus is not None and astatus != 2) or atype in ('preview', 'storyboard'):
  78. continue
  79. elif atype in ('still', 'still_image'):
  80. thumbnails.append({
  81. 'url': aurl,
  82. 'width': int_or_none(a.get('width')),
  83. 'height': int_or_none(a.get('height')),
  84. })
  85. else:
  86. aext = a.get('ext')
  87. is_m3u8 = a.get('container') == 'm3u8' or aext == 'm3u8'
  88. formats.append({
  89. 'format_id': atype,
  90. 'url': aurl,
  91. 'tbr': int_or_none(a.get('bitrate')),
  92. 'vbr': int_or_none(a.get('opt_vbitrate')),
  93. 'width': int_or_none(a.get('width')),
  94. 'height': int_or_none(a.get('height')),
  95. 'filesize': int_or_none(a.get('size')),
  96. 'vcodec': a.get('codec'),
  97. 'container': a.get('container'),
  98. 'ext': 'mp4' if is_m3u8 else aext,
  99. 'protocol': 'm3u8' if is_m3u8 else None,
  100. 'preference': 1 if atype == 'original' else None,
  101. })
  102. self._sort_formats(formats)
  103. return {
  104. 'id': video_id,
  105. 'title': title,
  106. 'description': data.get('seoDescription'),
  107. 'formats': formats,
  108. 'thumbnails': thumbnails,
  109. 'duration': float_or_none(data.get('duration')),
  110. 'timestamp': int_or_none(data.get('createdAt')),
  111. }