0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-18 01:35:12 +00:00
yt-dlp/youtube_dl/extractor/m6.py
2014-11-23 21:39:15 +01:00

56 lines
1.9 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.

# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class M6IE(InfoExtractor):
IE_NAME = 'm6'
_VALID_URL = r'http://(?:www\.)?m6\.fr/[^/]+/videos/(?P<id>\d+)-[^\.]+\.html'
_TEST = {
'url': 'http://www.m6.fr/emission-les_reines_du_shopping/videos/11323908-emeline_est_la_reine_du_shopping_sur_le_theme_ma_fete_d_8217_anniversaire.html',
'md5': '242994a87de2c316891428e0176bcb77',
'info_dict': {
'id': '11323908',
'ext': 'mp4',
'title': 'Emeline est la Reine du Shopping sur le thème « Ma fête danniversaire ! »',
'description': 'md5:1212ae8fb4b7baa4dc3886c5676007c2',
'duration': 100,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
rss = self._download_xml('http://ws.m6.fr/v1/video/info/m6/bonus/%s' % video_id, video_id,
'Downloading video RSS')
title = rss.find('./channel/item/title').text
description = rss.find('./channel/item/description').text
thumbnail = rss.find('./channel/item/visuel_clip_big').text
duration = int(rss.find('./channel/item/duration').text)
view_count = int(rss.find('./channel/item/nombre_vues').text)
formats = []
for format_id in ['lq', 'sd', 'hq', 'hd']:
video_url = rss.find('./channel/item/url_video_%s' % format_id)
if video_url is None:
continue
formats.append({
'url': video_url.text,
'format_id': format_id,
})
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'formats': formats,
}