Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ina.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     int_or_none,
   8     strip_or_none,
   9     xpath_attr,
  10     xpath_text,
  11 )
  12
  13
  14 class InaIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?ina\.fr/(?:video|audio)/(?P<id>[A-Z0-9_]+)'
  16     _TESTS = [{
  17         'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
  18         'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
  19         'info_dict': {
  20             'id': 'I12055569',
  21             'ext': 'mp4',
  22             'title': 'François Hollande "Je crois que c\'est clair"',
  23             'description': 'md5:3f09eb072a06cb286b8f7e4f77109663',
  24         }
  25     }, {
  26         'url': 'https://www.ina.fr/video/S806544_001/don-d-organes-des-avancees-mais-d-importants-besoins-video.html',
  27         'only_matching': True,
  28     }, {
  29         'url': 'https://www.ina.fr/audio/P16173408',
  30         'only_matching': True,
  31     }, {
  32         'url': 'https://www.ina.fr/video/P16173408-video.html',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38         info_doc = self._download_xml(
  39             'http://player.ina.fr/notices/%s.mrss' % video_id, video_id)
  40         item = info_doc.find('channel/item')
  41         title = xpath_text(item, 'title', fatal=True)
  42         media_ns_xpath = lambda x: self._xpath_ns(x, 'http://search.yahoo.com/mrss/')
  43         content = item.find(media_ns_xpath('content'))
  44
  45         get_furl = lambda x: xpath_attr(content, media_ns_xpath(x), 'url')
  46         formats = []
  47         for q, w, h in (('bq', 400, 300), ('mq', 512, 384), ('hq', 768, 576)):
  48             q_url = get_furl(q)
  49             if not q_url:
  50                 continue
  51             formats.append({
  52                 'format_id': q,
  53                 'url': q_url,
  54                 'width': w,
  55                 'height': h,
  56             })
  57         if not formats:
  58             furl = get_furl('player') or content.attrib['url']
  59             ext = determine_ext(furl)
  60             formats = [{
  61                 'url': furl,
  62                 'vcodec': 'none' if ext == 'mp3' else None,
  63                 'ext': ext,
  64             }]
  65
  66         thumbnails = []
  67         for thumbnail in content.findall(media_ns_xpath('thumbnail')):
  68             thumbnail_url = thumbnail.get('url')
  69             if not thumbnail_url:
  70                 continue
  71             thumbnails.append({
  72                 'url': thumbnail_url,
  73                 'height': int_or_none(thumbnail.get('height')),
  74                 'width': int_or_none(thumbnail.get('width')),
  75             })
  76
  77         return {
  78             'id': video_id,
  79             'formats': formats,
  80             'title': title,
  81             'description': strip_or_none(xpath_text(item, 'description')),
  82             'thumbnails': thumbnails,
  83         }