1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-28 05:02:59 +08:00
youtube-dl/youtube_dl/extractor/franceinter.py

50 lines
1.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import int_or_none
class FranceInterIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
'md5': '4764932e466e6f6c79c317d2e74f6884',
'info_dict': {
'id': '793962',
'ext': 'mp3',
'title': 'LHistoire dans les jeux vidéo',
'description': 'md5:7e93ddb4451e7530022792240a3049c7',
'timestamp': 1387369800,
'upload_date': '20131218',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
path = self._search_regex(
r'<a id="player".+?href="([^"]+)"', webpage, 'video url')
video_url = 'http://www.franceinter.fr/' + path
title = self._html_search_regex(
r'<span class="title-diffusion">(.+?)</span>', webpage, 'title')
description = self._html_search_regex(
r'<span class="description">(.*?)</span>',
webpage, 'description', fatal=False)
timestamp = int_or_none(self._search_regex(
r'data-date="(\d+)"', webpage, 'upload date', fatal=False))
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'formats': [{
'url': video_url,
'vcodec': 'none',
}],
}