Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/infoq.py

   1 from __future__ import unicode_literals
   2
   3 import base64
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse,
   9 )
  10
  11
  12 class InfoQIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
  14
  15     _TEST = {
  16         'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
  17         'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
  18         'info_dict': {
  19             'id': '12-jan-pythonthings',
  20             'ext': 'mp4',
  21             'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
  22             'title': 'A Few of My Favorite [Python] Things',
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group('id')
  29
  30         webpage = self._download_webpage(url, video_id)
  31
  32         video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
  33         video_description = self._html_search_meta('description', webpage, 'description')
  34
  35         # The server URL is hardcoded
  36         video_url = 'rtmpe://video.infoq.com/cfx/st/'
  37
  38         # Extract video URL
  39         encoded_id = self._search_regex(
  40             r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id')
  41         real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
  42         playpath = 'mp4:' + real_id
  43
  44         video_filename = playpath.split('/')[-1]
  45         video_id, extension = video_filename.split('.')
  46
  47         http_base = self._search_regex(
  48             r'EXPRESSINSTALL_SWF\s*=\s*"(https?://[^/"]+/)', webpage,
  49             'HTTP base URL')
  50
  51         formats = [{
  52             'format_id': 'rtmp',
  53             'url': video_url,
  54             'ext': extension,
  55             'play_path': playpath,
  56         }, {
  57             'format_id': 'http',
  58             'url': http_base + real_id,
  59         }]
  60         self._sort_formats(formats)
  61
  62         return {
  63             'id': video_id,
  64             'title': video_title,
  65             'description': video_description,
  66             'formats': formats,
  67         }