yt-dlp/youtube_dl/extractor/tf1.py

49 lines
1.9 KiB
Python
Raw Normal View History

2013-06-29 15:18:19 +02:00
# coding: utf-8
2014-03-29 15:05:15 +01:00
from __future__ import unicode_literals
2013-06-29 15:18:19 +02:00
import re
from .common import InfoExtractor
2014-03-29 15:05:15 +01:00
2013-06-29 15:18:19 +02:00
class TF1IE(InfoExtractor):
"""TF1 uses the wat.tv player."""
2015-01-04 01:05:31 +01:00
_VALID_URL = r'http://(?:videos\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html'
_TESTS = {
2014-03-29 15:05:15 +01:00
'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
'info_dict': {
'id': '10635995',
'ext': 'mp4',
'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle',
'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
},
'params': {
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
},
2015-01-04 01:05:31 +01:00
}, {
'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
'info_dict': {
'id': '7085291',
'ext': 'mp4',
'title': 'Le grand Mystérioso - Chuggington',
'description': 'Emery rêve qu\'un article lui soit consacré dans le journal.',
},
'params': {
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
},
2013-06-29 15:18:19 +02:00
}
def _real_extract(self, url):
2015-01-04 01:05:31 +01:00
video_id = self._match_id(url)
2014-03-29 15:05:15 +01:00
webpage = self._download_webpage(url, video_id)
embed_url = self._html_search_regex(
2015-01-04 01:05:31 +01:00
r'["\'](http(?:s)?://www.wat.tv/embedframe/.*?)["\']', webpage, 'embed url')
2014-03-29 15:05:15 +01:00
embed_page = self._download_webpage(embed_url, video_id,
2014-11-23 21:39:15 +01:00
'Downloading embed player page')
2013-06-29 15:18:19 +02:00
wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')
2014-03-29 15:05:15 +01:00
wat_info = self._download_json(
'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id)
return self.url_result(wat_info['media']['url'], 'Wat')