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