logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

infoq.py (5189B)

    

  1. # coding: utf-8
  3. from __future__ import unicode_literals
  4. from ..utils import (
  5.     ExtractorError,
  6. )
  8. from ..compat import (
  9.     compat_b64decode,
  10.     compat_urllib_parse_unquote,
  11.     compat_urlparse,
  12. )
  13. from ..utils import (
  14.     determine_ext,
  15.     update_url_query,
  16. )
  17. from .bokecc import BokeCCBaseIE
  20. class InfoQIE(BokeCCBaseIE):
  21.     _VALID_URL = r'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P<id>[^/]+)'
  23.     _TESTS = [{
  24.         'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
  25.         'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
  26.         'info_dict': {
  27.             'id': 'A-Few-of-My-Favorite-Python-Things',
  28.             'ext': 'mp4',
  29.             'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
  30.             'title': 'A Few of My Favorite [Python] Things',
  31.         },
  32.     }, {
  33.         'url': 'http://www.infoq.com/fr/presentations/changez-avis-sur-javascript',
  34.         'only_matching': True,
  35.     }, {
  36.         'url': 'http://www.infoq.com/cn/presentations/openstack-continued-delivery',
  37.         'md5': '4918d0cca1497f2244572caf626687ef',
  38.         'info_dict': {
  39.             'id': 'openstack-continued-delivery',
  40.             'title': 'OpenStack持续交付之路',
  41.             'ext': 'flv',
  42.             'description': 'md5:308d981fb28fa42f49f9568322c683ff',
  43.         },
  44.     }, {
  45.         'url': 'https://www.infoq.com/presentations/Simple-Made-Easy',
  46.         'md5': '0e34642d4d9ef44bf86f66f6399672db',
  47.         'info_dict': {
  48.             'id': 'Simple-Made-Easy',
  49.             'title': 'Simple Made Easy',
  50.             'ext': 'mp3',
  51.             'description': 'md5:3e0e213a8bbd074796ef89ea35ada25b',
  52.         },
  53.         'params': {
  54.             'format': 'bestaudio',
  55.         },
  56.     }]
  58.     def _extract_rtmp_video(self, webpage):
  59.         # The server URL is hardcoded
  60.         video_url = 'rtmpe://videof.infoq.com/cfx/st/'
  62.         # Extract video URL
  63.         encoded_id = self._search_regex(
  64.             r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id', default=None)
  66.         real_id = compat_urllib_parse_unquote(compat_b64decode(encoded_id).decode('utf-8'))
  67.         playpath = 'mp4:' + real_id
  69.         return [{
  70.             'format_id': 'rtmp_video',
  71.             'url': video_url,
  72.             'ext': determine_ext(playpath),
  73.             'play_path': playpath,
  74.         }]
  76.     def _extract_cf_auth(self, webpage):
  77.         policy = self._search_regex(r'InfoQConstants\.scp\s*=\s*\'([^\']+)\'', webpage, 'policy')
  78.         signature = self._search_regex(r'InfoQConstants\.scs\s*=\s*\'([^\']+)\'', webpage, 'signature')
  79.         key_pair_id = self._search_regex(r'InfoQConstants\.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id')
  80.         return {
  81.             'Policy': policy,
  82.             'Signature': signature,
  83.             'Key-Pair-Id': key_pair_id,
  84.         }
  86.     def _extract_http_video(self, webpage):
  87.         http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL')
  88.         http_video_url = update_url_query(http_video_url, self._extract_cf_auth(webpage))
  89.         return [{
  90.             'format_id': 'http_video',
  91.             'url': http_video_url,
  92.             'http_headers': {'Referer': 'https://www.infoq.com/'},
  93.         }]
  95.     def _extract_http_audio(self, webpage, video_id):
  96.         try:
  97.             fields = self._form_hidden_inputs('mp3Form', webpage)
  98.         except ExtractorError:
  99.             fields = {}
  101.         http_audio_url = fields.get('filename')
  102.         if not http_audio_url:
  103.             return []
  105.         # base URL is found in the Location header in the response returned by
  106.         # GET https://www.infoq.com/mp3download.action?filename=... when logged in.
  107.         http_audio_url = compat_urlparse.urljoin('http://ress.infoq.com/downloads/mp3downloads/', http_audio_url)
  108.         http_audio_url = update_url_query(http_audio_url, self._extract_cf_auth(webpage))
  110.         # audio file seem to be missing some times even if there is a download link
  111.         # so probe URL to make sure
  112.         if not self._is_valid_url(http_audio_url, video_id):
  113.             return []
  115.         return [{
  116.             'format_id': 'http_audio',
  117.             'url': http_audio_url,
  118.             'vcodec': 'none',
  119.         }]
  121.     def _real_extract(self, url):
  122.         video_id = self._match_id(url)
  123.         webpage = self._download_webpage(url, video_id)
  125.         video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
  126.         video_description = self._html_search_meta('description', webpage, 'description')
  128.         if '/cn/' in url:
  129.             # for China videos, HTTP video URL exists but always fails with 403
  130.             formats = self._extract_bokecc_formats(webpage, video_id)
  131.         else:
  132.             formats = (
  133.                 self._extract_rtmp_video(webpage)
  134.                 + self._extract_http_video(webpage)
  135.                 + self._extract_http_audio(webpage, video_id))
  137.         self._sort_formats(formats)
  139.         return {
  140.             'id': video_id,
  141.             'title': video_title,
  142.             'description': video_description,
  143.             'formats': formats,
  144.         }