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.

141 lines
5.8 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'http://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': 'flv',
  54. 'title': 'Integrated Senate Video Player',
  55. 'thumbnail': 're:^https?://.*\.(?:jpg|png)$',
  56. }
  57. }, {
  58. 'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
  59. 'info_dict': {
  60. 'id': 'commerce011514',
  61. 'ext': 'flv',
  62. 'title': 'Integrated Senate Video Player'
  63. }
  64. }, {
  65. 'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
  66. # checksum differs each time
  67. 'info_dict': {
  68. 'id': 'intel090613',
  69. 'ext': 'mp4',
  70. 'title': 'Integrated Senate Video Player'
  71. }
  72. }]
  73. @staticmethod
  74. def _search_iframe_url(webpage):
  75. mobj = re.search(
  76. r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/\?[^'\"]+)['\"]",
  77. webpage)
  78. if mobj:
  79. return mobj.group('url')
  80. def _get_info_for_comm(self, committee):
  81. for entry in self._COMM_MAP:
  82. if entry[0] == committee:
  83. return entry[1:]
  84. def _real_extract(self, url):
  85. url, smuggled_data = unsmuggle_url(url, {})
  86. qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs'))
  87. if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
  88. raise ExtractorError('Invalid URL', expected=True)
  89. video_id = re.sub(r'.mp4$', '', qs['filename'][0])
  90. webpage = self._download_webpage(url, video_id)
  91. if smuggled_data.get('force_title'):
  92. title = smuggled_data['force_title']
  93. else:
  94. title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
  95. poster = qs.get('poster')
  96. thumbnail = poster[0] if poster else None
  97. video_type = qs['type'][0]
  98. committee = video_type if video_type == 'arch' else qs['comm'][0]
  99. stream_num, domain = self._get_info_for_comm(committee)
  100. formats = []
  101. if video_type == 'arch':
  102. filename = video_id if '.' in video_id else video_id + '.mp4'
  103. formats = [{
  104. # All parameters in the query string are necessary to prevent a 403 error
  105. 'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
  106. }]
  107. else:
  108. hdcore_sign = '?hdcore=3.1.0'
  109. url_params = (domain, video_id, stream_num)
  110. f4m_url = '%s/z/%s_1@%s/manifest.f4m' % url_params + hdcore_sign
  111. m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
  112. for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
  113. # URLs without the extra param induce an 404 error
  114. entry.update({'extra_param_to_segment_url': hdcore_sign})
  115. formats.append(entry)
  116. for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
  117. mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
  118. if mobj:
  119. entry['format_id'] += mobj.group('tag')
  120. formats.append(entry)
  121. self._sort_formats(formats)
  122. return {
  123. 'id': video_id,
  124. 'title': title,
  125. 'formats': formats,
  126. 'thumbnail': thumbnail,
  127. }