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     ExtractorError,
  12 )
  13
  14
  15 class FranceCultureIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
  17     _TEST = {
  18         'url': 'http://www.franceculture.fr/player/reecouter?play=4795174',
  19         'info_dict': {
  20             'id': '4795174',
  21             'ext': 'mp3',
  22             'title': 'Rendez-vous au pays des geeks',
  23             'alt_title': 'Carnet nomade | 13-14',
  24             'vcodec': 'none',
  25             'upload_date': '20140301',
  26             'thumbnail': r're:^http://static\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
  27             'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche',
  28             'timestamp': 1393700400,
  29         }
  30     }
  31
  32     def _extract_from_player(self, url, video_id):
  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         display_id = self._search_regex(
  46             r'<span class="path-diffusion">emission-(.*?)</span>', webpage, 'display_id')
  47
  48         title = self._html_search_regex(
  49             r'<span class="title-diffusion">(.*?)</span>', webpage, 'title')
  50         alt_title = self._html_search_regex(
  51             r'<span class="title">(.*?)</span>',
  52             webpage, 'alt_title', fatal=False)
  53         description = self._html_search_regex(
  54             r'<span class="description">(.*?)</span>',
  55             webpage, 'description', fatal=False)
  56
  57         uploader = self._html_search_regex(
  58             r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
  59             webpage, 'uploader', default=None)
  60         vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None
  61
  62         return {
  63             'id': video_id,
  64             'url': video_url,
  65             'vcodec': vcodec,
  66             'uploader': uploader,
  67             'timestamp': timestamp,
  68             'title': title,
  69             'alt_title': alt_title,
  70             'thumbnail': thumbnail,
  71             'description': description,
  72             'display_id': display_id,
  73         }
  74
  75     def _real_extract(self, url):
  76         video_id = self._match_id(url)
  77         return self._extract_from_player(url, video_id)
  78
  79
  80 class FranceCultureEmissionIE(FranceCultureIE):
  81     _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emission-(?P<id>[^?#]+)'
  82     _TEST = {
  83         'url': 'http://www.franceculture.fr/emission-les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
  84         'info_dict': {
  85             'title': 'Jean-Gabriel Périot, cinéaste',
  86             'alt_title': 'Les Carnets de la création',
  87             'id': '5093239',
  88             'display_id': 'les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
  89             'ext': 'mp3',
  90             'timestamp': 1444762500,
  91             'upload_date': '20151013',
  92             'description': 'startswith:Aujourd\'hui dans "Les carnets de la création", le cinéaste',
  93         },
  94     }
  95
  96     def _real_extract(self, url):
  97         video_id = self._match_id(url)
  98         webpage = self._download_webpage(url, video_id)
  99         video_path = self._html_search_regex(
 100             r'<a class="rf-player-open".*?href="([^"]+)"', webpage, 'video path', 'no_path_player')
 101         if video_path == 'no_path_player':
 102             raise ExtractorError('no player : no sound in this page.', expected=True)
 103         new_id = self._search_regex('play=(?P<id>[0-9]+)', video_path, 'new_id', group='id')
 104         video_url = compat_urlparse.urljoin(url, video_path)
 105         return self._extract_from_player(video_url, new_id)