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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_urlparse,
   7 )
   8 from ..utils import (
   9     determine_ext,
  10     int_or_none,
  11 )
  12
  13
  14 class FranceCultureIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
  16     _TEST = {
  17         'url': 'http://www.franceculture.fr/player/reecouter?play=4795174',
  18         'info_dict': {
  19             'id': '4795174',
  20             'ext': 'mp3',
  21             'title': 'Rendez-vous au pays des geeks',
  22             'alt_title': 'Carnet nomade | 13-14',
  23             'vcodec': 'none',
  24             'upload_date': '20140301',
  25             'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
  26             'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats',
  27             'timestamp': 1393700400,
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         webpage = self._download_webpage(url, video_id)
  34
  35         video_path = self._search_regex(
  36             r'<a id="player".*?href="([^"]+)"', webpage, 'video path')
  37         video_url = compat_urlparse.urljoin(url, video_path)
  38         timestamp = int_or_none(self._search_regex(
  39             r'<a id="player".*?data-date="([0-9]+)"',
  40             webpage, 'upload date', fatal=False))
  41         thumbnail = self._search_regex(
  42             r'<a id="player".*?>\s+<img src="([^"]+)"',
  43             webpage, 'thumbnail', fatal=False)
  44
  45         title = self._html_search_regex(
  46             r'<span class="title-diffusion">(.*?)</span>', webpage, 'title')
  47         alt_title = self._html_search_regex(
  48             r'<span class="title">(.*?)</span>',
  49             webpage, 'alt_title', fatal=False)
  50         description = self._html_search_regex(
  51             r'<span class="description">(.*?)</span>',
  52             webpage, 'description', fatal=False)
  53
  54         uploader = self._html_search_regex(
  55             r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
  56             webpage, 'uploader', default=None)
  57         vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None
  58
  59         return {
  60             'id': video_id,
  61             'url': video_url,
  62             'vcodec': vcodec,
  63             'uploader': uploader,
  64             'timestamp': timestamp,
  65             'title': title,
  66             'alt_title': alt_title,
  67             'thumbnail': thumbnail,
  68             'description': description,
  69         }