ytdl-nightly/youtube_dl/extractor/franceinter.py

39 lines
1.1 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
2014-01-15 07:19:50 +01:00
import re
from .common import InfoExtractor
2014-01-15 07:19:50 +01:00
class FranceInterIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})'
_TEST = {
'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
'file': '793962.mp3',
'md5': '4764932e466e6f6c79c317d2e74f6884',
"info_dict": {
"title": "LHistoire dans les jeux vidéo",
},
}
2014-01-15 07:19:50 +01:00
def _real_extract(self, url):
2014-01-15 07:19:50 +01:00
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<span class="roll_overflow">(.*?)</span></h1>', webpage, 'title')
path = self._search_regex(
r'&urlAOD=(.*?)&startTime', webpage, 'video url')
video_url = 'http://www.franceinter.fr/' + path
return {
'id': video_id,
'formats': [{
'url': video_url,
'vcodec': 'none',
}],
'title': title,
}