_ Git - youtube-dl/blob - youtube_dl/extractor/franceculture.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7     extract_attributes,
   8     int_or_none,
   9 )
  10
  11
  12 class FranceCultureIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)'
  14     _TEST = {
  15         'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks',
  16         'info_dict': {
  17             'id': 'rendez-vous-au-pays-des-geeks',
  18             'display_id': 'rendez-vous-au-pays-des-geeks',
  19             'ext': 'mp3',
  20             'title': 'Rendez-vous au pays des geeks',
  21             'thumbnail': r're:^https?://.*\.jpg$',
  22             'upload_date': '20140301',
  23             'timestamp': 1393642916,
  24             'vcodec': 'none',
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         display_id = self._match_id(url)
  30
  31         webpage = self._download_webpage(url, display_id)
  32
  33         video_data = extract_attributes(self._search_regex(
  34             r'''(?sx)
  35                 (?:
  36                     </h1>|
  37                     <div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>
  38                 ).*?
  39                 (<button[^>]+data-asset-source="[^"]+"[^>]+>)
  40             ''',
  41             webpage, 'video data'))
  42
  43         video_url = video_data['data-asset-source']
  44         title = video_data.get('data-asset-title') or self._og_search_title(webpage)
  45
  46         description = self._html_search_regex(
  47             r'(?s)<div[^>]+class="intro"[^>]*>.*?<h2>(.+?)</h2>',
  48             webpage, 'description', default=None)
  49         thumbnail = self._search_regex(
  50             r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+(?:data-dejavu-)?src="([^"]+)"',
  51             webpage, 'thumbnail', fatal=False)
  52         uploader = self._html_search_regex(
  53             r'(?s)<span class="author">(.*?)</span>',
  54             webpage, 'uploader', default=None)
  55         ext = determine_ext(video_url.lower())
  56
  57         return {
  58             'id': display_id,
  59             'display_id': display_id,
  60             'url': video_url,
  61             'title': title,
  62             'description': description,
  63             'thumbnail': thumbnail,
  64             'ext': ext,
  65             'vcodec': 'none' if ext == 'mp3' else None,
  66             'uploader': uploader,
  67             'timestamp': int_or_none(video_data.get('data-asset-created-date')),
  68             'duration': int_or_none(video_data.get('data-duration')),
  69         }