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.

153 lines
6.1 KiB

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import re
  4. from .common import InfoExtractor
  5. from ..utils import (
  6. ExtractorError,
  7. unsmuggle_url,
  8. )
  9. from ..compat import (
  10. compat_parse_qs,
  11. compat_urlparse,
  12. )
  13. class SenateISVPIE(InfoExtractor):
  14. _COMM_MAP = [
  15. ['ag', '76440', 'http://ag-f.akamaihd.net'],
  16. ['aging', '76442', 'http://aging-f.akamaihd.net'],
  17. ['approps', '76441', 'http://approps-f.akamaihd.net'],
  18. ['armed', '76445', 'http://armed-f.akamaihd.net'],
  19. ['banking', '76446', 'http://banking-f.akamaihd.net'],
  20. ['budget', '76447', 'http://budget-f.akamaihd.net'],
  21. ['cecc', '76486', 'http://srs-f.akamaihd.net'],
  22. ['commerce', '80177', 'http://commerce1-f.akamaihd.net'],
  23. ['csce', '75229', 'http://srs-f.akamaihd.net'],
  24. ['dpc', '76590', 'http://dpc-f.akamaihd.net'],
  25. ['energy', '76448', 'http://energy-f.akamaihd.net'],
  26. ['epw', '76478', 'http://epw-f.akamaihd.net'],
  27. ['ethics', '76449', 'http://ethics-f.akamaihd.net'],
  28. ['finance', '76450', 'http://finance-f.akamaihd.net'],
  29. ['foreign', '76451', 'http://foreign-f.akamaihd.net'],
  30. ['govtaff', '76453', 'http://govtaff-f.akamaihd.net'],
  31. ['help', '76452', 'http://help-f.akamaihd.net'],
  32. ['indian', '76455', 'http://indian-f.akamaihd.net'],
  33. ['intel', '76456', 'http://intel-f.akamaihd.net'],
  34. ['intlnarc', '76457', 'http://intlnarc-f.akamaihd.net'],
  35. ['jccic', '85180', 'http://jccic-f.akamaihd.net'],
  36. ['jec', '76458', 'http://jec-f.akamaihd.net'],
  37. ['judiciary', '76459', 'http://judiciary-f.akamaihd.net'],
  38. ['rpc', '76591', 'http://rpc-f.akamaihd.net'],
  39. ['rules', '76460', 'http://rules-f.akamaihd.net'],
  40. ['saa', '76489', 'http://srs-f.akamaihd.net'],
  41. ['smbiz', '76461', 'http://smbiz-f.akamaihd.net'],
  42. ['srs', '75229', 'http://srs-f.akamaihd.net'],
  43. ['uscc', '76487', 'http://srs-f.akamaihd.net'],
  44. ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
  45. ['arch', '', 'http://ussenate-f.akamaihd.net/']
  46. ]
  47. _IE_NAME = 'senate.gov'
  48. _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
  49. _TESTS = [{
  50. 'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',
  51. 'info_dict': {
  52. 'id': 'judiciary031715',
  53. 'ext': 'mp4',
  54. 'title': 'Integrated Senate Video Player',
  55. 'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
  56. },
  57. 'params': {
  58. # m3u8 download
  59. 'skip_download': True,
  60. },
  61. }, {
  62. 'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
  63. 'info_dict': {
  64. 'id': 'commerce011514',
  65. 'ext': 'mp4',
  66. 'title': 'Integrated Senate Video Player'
  67. },
  68. 'params': {
  69. # m3u8 download
  70. 'skip_download': True,
  71. },
  72. }, {
  73. 'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
  74. # checksum differs each time
  75. 'info_dict': {
  76. 'id': 'intel090613',
  77. 'ext': 'mp4',
  78. 'title': 'Integrated Senate Video Player'
  79. }
  80. }, {
  81. # From http://www.c-span.org/video/?96791-1
  82. 'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715',
  83. 'only_matching': True,
  84. }]
  85. @staticmethod
  86. def _search_iframe_url(webpage):
  87. mobj = re.search(
  88. r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
  89. webpage)
  90. if mobj:
  91. return mobj.group('url')
  92. def _get_info_for_comm(self, committee):
  93. for entry in self._COMM_MAP:
  94. if entry[0] == committee:
  95. return entry[1:]
  96. def _real_extract(self, url):
  97. url, smuggled_data = unsmuggle_url(url, {})
  98. qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs'))
  99. if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
  100. raise ExtractorError('Invalid URL', expected=True)
  101. video_id = re.sub(r'.mp4$', '', qs['filename'][0])
  102. webpage = self._download_webpage(url, video_id)
  103. if smuggled_data.get('force_title'):
  104. title = smuggled_data['force_title']
  105. else:
  106. title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
  107. poster = qs.get('poster')
  108. thumbnail = poster[0] if poster else None
  109. video_type = qs['type'][0]
  110. committee = video_type if video_type == 'arch' else qs['comm'][0]
  111. stream_num, domain = self._get_info_for_comm(committee)
  112. formats = []
  113. if video_type == 'arch':
  114. filename = video_id if '.' in video_id else video_id + '.mp4'
  115. formats = [{
  116. # All parameters in the query string are necessary to prevent a 403 error
  117. 'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
  118. }]
  119. else:
  120. hdcore_sign = 'hdcore=3.1.0'
  121. url_params = (domain, video_id, stream_num)
  122. f4m_url = '%s/z/%s_1@%s/manifest.f4m?' % url_params + hdcore_sign
  123. m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
  124. for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
  125. # URLs without the extra param induce an 404 error
  126. entry.update({'extra_param_to_segment_url': hdcore_sign})
  127. formats.append(entry)
  128. for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
  129. mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
  130. if mobj:
  131. entry['format_id'] += mobj.group('tag')
  132. formats.append(entry)
  133. self._sort_formats(formats)
  134. return {
  135. 'id': video_id,
  136. 'title': title,
  137. 'formats': formats,
  138. 'thumbnail': thumbnail,
  139. }