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.

169 lines
7.7 KiB

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import re
  4. from .common import InfoExtractor
  5. from ..compat import (
  6. compat_parse_qs,
  7. compat_str,
  8. compat_urllib_parse_urlparse,
  9. )
  10. from ..utils import (
  11. urljoin,
  12. int_or_none,
  13. parse_codecs,
  14. try_get,
  15. )
  16. def _raw_id(src_url):
  17. return compat_urllib_parse_urlparse(src_url).path.split('/')[-1]
  18. class SeznamZpravyIE(InfoExtractor):
  19. _VALID_URL = r'https?://(?:www\.)?seznamzpravy\.cz/iframe/player\?.*\bsrc='
  20. _TESTS = [{
  21. 'url': 'https://www.seznamzpravy.cz/iframe/player?duration=241&serviceSlug=zpravy&src=https%3A%2F%2Fv39-a.sdn.szn.cz%2Fv_39%2Fvmd%2F5999c902ea707c67d8e267a9%3Ffl%3Dmdk%2C432f65a0%7C&itemType=video&autoPlay=false&title=Sv%C4%9Bt%20bez%20obalu%3A%20%C4%8Ce%C5%A1t%C3%AD%20voj%C3%A1ci%20na%20mis%C3%ADch%20(kr%C3%A1tk%C3%A1%20verze)&series=Sv%C4%9Bt%20bez%20obalu&serviceName=Seznam%20Zpr%C3%A1vy&poster=%2F%2Fd39-a.sdn.szn.cz%2Fd_39%2Fc_img_F_I%2FR5puJ.jpeg%3Ffl%3Dcro%2C0%2C0%2C1920%2C1080%7Cres%2C1200%2C%2C1%7Cjpg%2C80%2C%2C1&width=1920&height=1080&cutFrom=0&cutTo=0&splVersion=VOD&contentId=170889&contextId=35990&showAdvert=true&collocation=&autoplayPossible=true&embed=&isVideoTooShortForPreroll=false&isVideoTooLongForPostroll=true&videoCommentOpKey=&videoCommentId=&version=4.0.76&dotService=zpravy&gemiusPrismIdentifier=bVc1ZIb_Qax4W2v5xOPGpMeCP31kFfrTzj0SqPTLh_b.Z7&zoneIdPreroll=seznam.pack.videospot&skipOffsetPreroll=5&sectionPrefixPreroll=%2Fzpravy',
  22. 'info_dict': {
  23. 'id': '170889',
  24. 'ext': 'mp4',
  25. 'title': 'Svět bez obalu: Čeští vojáci na misích (krátká verze)',
  26. 'thumbnail': r're:^https?://.*\.jpe?g',
  27. 'duration': 241,
  28. 'series': 'Svět bez obalu',
  29. },
  30. 'params': {
  31. 'skip_download': True,
  32. },
  33. }, {
  34. # with Location key
  35. 'url': 'https://www.seznamzpravy.cz/iframe/player?duration=null&serviceSlug=zpravy&src=https%3A%2F%2Flive-a.sdn.szn.cz%2Fv_39%2F59e468fe454f8472a96af9fa%3Ffl%3Dmdk%2C5c1e2840%7C&itemType=livevod&autoPlay=false&title=P%C5%99edseda%20KDU-%C4%8CSL%20Pavel%20B%C4%9Blobr%C3%A1dek%20ve%20volebn%C3%AD%20V%C3%BDzv%C4%9B%20Seznamu&series=V%C3%BDzva&serviceName=Seznam%20Zpr%C3%A1vy&poster=%2F%2Fd39-a.sdn.szn.cz%2Fd_39%2Fc_img_G_J%2FjTBCs.jpeg%3Ffl%3Dcro%2C0%2C0%2C1280%2C720%7Cres%2C1200%2C%2C1%7Cjpg%2C80%2C%2C1&width=16&height=9&cutFrom=0&cutTo=0&splVersion=VOD&contentId=185688&contextId=38489&showAdvert=true&collocation=&hideFullScreen=false&hideSubtitles=false&embed=&isVideoTooShortForPreroll=false&isVideoTooShortForPreroll2=false&isVideoTooLongForPostroll=false&fakePostrollZoneID=seznam.clanky.zpravy.preroll&fakePrerollZoneID=seznam.clanky.zpravy.preroll&videoCommentId=&trim=default_16x9&noPrerollVideoLength=30&noPreroll2VideoLength=undefined&noMidrollVideoLength=0&noPostrollVideoLength=999999&autoplayPossible=true&version=5.0.41&dotService=zpravy&gemiusPrismIdentifier=zD3g7byfW5ekpXmxTVLaq5Srjw5i4hsYo0HY1aBwIe..27&zoneIdPreroll=seznam.pack.videospot&skipOffsetPreroll=5&sectionPrefixPreroll=%2Fzpravy%2Fvyzva&zoneIdPostroll=seznam.pack.videospot&skipOffsetPostroll=5&sectionPrefixPostroll=%2Fzpravy%2Fvyzva&regression=false',
  36. 'info_dict': {
  37. 'id': '185688',
  38. 'ext': 'mp4',
  39. 'title': 'Předseda KDU-ČSL Pavel Bělobrádek ve volební Výzvě Seznamu',
  40. 'thumbnail': r're:^https?://.*\.jpe?g',
  41. 'series': 'Výzva',
  42. },
  43. 'params': {
  44. 'skip_download': True,
  45. },
  46. }]
  47. @staticmethod
  48. def _extract_urls(webpage):
  49. return [
  50. mobj.group('url') for mobj in re.finditer(
  51. r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?seznamzpravy\.cz/iframe/player\?.*?)\1',
  52. webpage)]
  53. def _extract_sdn_formats(self, sdn_url, video_id):
  54. sdn_data = self._download_json(sdn_url, video_id)
  55. if sdn_data.get('Location'):
  56. sdn_url = sdn_data['Location']
  57. sdn_data = self._download_json(sdn_url, video_id)
  58. formats = []
  59. mp4_formats = try_get(sdn_data, lambda x: x['data']['mp4'], dict) or {}
  60. for format_id, format_data in mp4_formats.items():
  61. relative_url = format_data.get('url')
  62. if not relative_url:
  63. continue
  64. try:
  65. width, height = format_data.get('resolution')
  66. except (TypeError, ValueError):
  67. width, height = None, None
  68. f = {
  69. 'url': urljoin(sdn_url, relative_url),
  70. 'format_id': 'http-%s' % format_id,
  71. 'tbr': int_or_none(format_data.get('bandwidth'), scale=1000),
  72. 'width': int_or_none(width),
  73. 'height': int_or_none(height),
  74. }
  75. f.update(parse_codecs(format_data.get('codec')))
  76. formats.append(f)
  77. pls = sdn_data.get('pls', {})
  78. def get_url(format_id):
  79. return try_get(pls, lambda x: x[format_id]['url'], compat_str)
  80. dash_rel_url = get_url('dash')
  81. if dash_rel_url:
  82. formats.extend(self._extract_mpd_formats(
  83. urljoin(sdn_url, dash_rel_url), video_id, mpd_id='dash',
  84. fatal=False))
  85. hls_rel_url = get_url('hls')
  86. if hls_rel_url:
  87. formats.extend(self._extract_m3u8_formats(
  88. urljoin(sdn_url, hls_rel_url), video_id, ext='mp4',
  89. m3u8_id='hls', fatal=False))
  90. self._sort_formats(formats)
  91. return formats
  92. def _real_extract(self, url):
  93. params = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
  94. src = params['src'][0]
  95. title = params['title'][0]
  96. video_id = params.get('contentId', [_raw_id(src)])[0]
  97. formats = self._extract_sdn_formats(src + 'spl2,2,VOD', video_id)
  98. duration = int_or_none(params.get('duration', [None])[0])
  99. series = params.get('series', [None])[0]
  100. thumbnail = params.get('poster', [None])[0]
  101. return {
  102. 'id': video_id,
  103. 'title': title,
  104. 'thumbnail': thumbnail,
  105. 'duration': duration,
  106. 'series': series,
  107. 'formats': formats,
  108. }
  109. class SeznamZpravyArticleIE(InfoExtractor):
  110. _VALID_URL = r'https?://(?:www\.)?(?:seznam\.cz/zpravy|seznamzpravy\.cz)/clanek/(?:[^/?#&]+)-(?P<id>\d+)'
  111. _API_URL = 'https://apizpravy.seznam.cz/'
  112. _TESTS = [{
  113. # two videos on one page, with SDN URL
  114. 'url': 'https://www.seznamzpravy.cz/clanek/jejich-svet-na-nas-utoci-je-lepsi-branit-se-na-jejich-pisecku-rika-reziser-a-major-v-zaloze-marhoul-35990',
  115. 'info_dict': {
  116. 'id': '35990',
  117. 'title': 'md5:6011c877a36905f28f271fcd8dcdb0f2',
  118. 'description': 'md5:933f7b06fa337a814ba199d3596d27ba',
  119. },
  120. 'playlist_count': 2,
  121. }, {
  122. # video with live stream URL
  123. 'url': 'https://www.seznam.cz/zpravy/clanek/znovu-do-vlady-s-ano-pavel-belobradek-ve-volebnim-specialu-seznamu-38489',
  124. 'info_dict': {
  125. 'id': '38489',
  126. 'title': 'md5:8fa1afdc36fd378cf0eba2b74c5aca60',
  127. 'description': 'md5:428e7926a1a81986ec7eb23078004fb4',
  128. },
  129. 'playlist_count': 1,
  130. }]
  131. def _real_extract(self, url):
  132. article_id = self._match_id(url)
  133. webpage = self._download_webpage(url, article_id)
  134. info = self._search_json_ld(webpage, article_id, default={})
  135. title = info.get('title') or self._og_search_title(webpage, fatal=False)
  136. description = info.get('description') or self._og_search_description(webpage)
  137. return self.playlist_result([
  138. self.url_result(entry_url, ie=SeznamZpravyIE.ie_key())
  139. for entry_url in SeznamZpravyIE._extract_urls(webpage)],
  140. article_id, title, description)