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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     parse_duration,
   9     parse_iso8601,
  10 )
  11
  12
  13 class RDSIE(InfoExtractor):
  14     IE_DESC = 'RDS.ca'
  15     _VALID_URL = r'https?://(?:www\.)?rds\.ca/vid(?:[eé]|%C3%A9)os/(?:[^/]+/)*(?P<display_id>[^/]+)-(?P<id>\d+\.\d+)'
  16
  17     _TESTS = [{
  18         'url': 'http://www.rds.ca/videos/football/nfl/fowler-jr-prend-la-direction-de-jacksonville-3.1132799',
  19         'info_dict': {
  20             'id': '3.1132799',
  21             'display_id': 'fowler-jr-prend-la-direction-de-jacksonville',
  22             'ext': 'mp4',
  23             'title': 'Fowler Jr. prend la direction de Jacksonville',
  24             'description': 'Dante Fowler Jr. est le troisième choix du repêchage 2015 de la NFL. ',
  25             'timestamp': 1430397346,
  26             'upload_date': '20150430',
  27             'duration': 154.354,
  28             'age_limit': 0,
  29         }
  30     }, {
  31         'url': 'http://www.rds.ca/vid%C3%A9os/un-voyage-positif-3.877934',
  32         'only_matching': True,
  33     }]
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         video_id = mobj.group('id')
  38         display_id = mobj.group('display_id')
  39
  40         webpage = self._download_webpage(url, display_id)
  41
  42         # TODO: extract f4m from 9c9media.com
  43         video_url = self._search_regex(
  44             r'<span[^>]+itemprop="contentURL"[^>]+content="([^"]+)"',
  45             webpage, 'video url')
  46
  47         title = self._og_search_title(webpage) or self._html_search_meta(
  48             'title', webpage, 'title', fatal=True)
  49         description = self._og_search_description(webpage) or self._html_search_meta(
  50             'description', webpage, 'description')
  51         thumbnail = self._og_search_thumbnail(webpage) or self._search_regex(
  52             [r'<link[^>]+itemprop="thumbnailUrl"[^>]+href="([^"]+)"',
  53              r'<span[^>]+itemprop="thumbnailUrl"[^>]+content="([^"]+)"'],
  54             webpage, 'thumbnail', fatal=False)
  55         timestamp = parse_iso8601(self._search_regex(
  56             r'<span[^>]+itemprop="uploadDate"[^>]+content="([^"]+)"',
  57             webpage, 'upload date', fatal=False))
  58         duration = parse_duration(self._search_regex(
  59             r'<span[^>]+itemprop="duration"[^>]+content="([^"]+)"',
  60             webpage, 'duration', fatal=False))
  61         age_limit = self._family_friendly_search(webpage)
  62
  63         return {
  64             'id': video_id,
  65             'display_id': display_id,
  66             'url': video_url,
  67             'title': title,
  68             'description': description,
  69             'thumbnail': thumbnail,
  70             'timestamp': timestamp,
  71             'duration': duration,
  72             'age_limit': age_limit,
  73         }