]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/canalc2.py
Imported Upstream version 2015.11.10
[youtubedl] / youtube_dl / extractor / canalc2.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import parse_duration
8
9
10 class Canalc2IE(InfoExtractor):
11 IE_NAME = 'canalc2.tv'
12 _VALID_URL = r'https?://(?:www\.)?canalc2\.tv/video/(?P<id>\d+)'
13
14 _TEST = {
15 'url': 'http://www.canalc2.tv/video/12163',
16 'md5': '060158428b650f896c542dfbb3d6487f',
17 'info_dict': {
18 'id': '12163',
19 'ext': 'flv',
20 'title': 'Terrasses du Numérique',
21 'duration': 122,
22 },
23 'params': {
24 'skip_download': True, # Requires rtmpdump
25 }
26 }
27
28 def _real_extract(self, url):
29 video_id = self._match_id(url)
30 webpage = self._download_webpage(url, video_id)
31 video_url = self._search_regex(
32 r'jwplayer\((["\'])Player\1\)\.setup\({[^}]*file\s*:\s*(["\'])(?P<file>.+?)\2',
33 webpage, 'video_url', group='file')
34 formats = [{'url': video_url}]
35 if video_url.startswith('rtmp://'):
36 rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
37 formats[0].update({
38 'url': rtmp.group('url'),
39 'ext': 'flv',
40 'app': rtmp.group('app'),
41 'play_path': rtmp.group('play_path'),
42 'page_url': url,
43 })
44
45 title = self._html_search_regex(
46 r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
47 duration = parse_duration(self._search_regex(
48 r'id=["\']video_duree["\'][^>]*>([^<]+)',
49 webpage, 'duration', fatal=False))
50
51 return {
52 'id': video_id,
53 'title': title,
54 'duration': duration,
55 'formats': formats,
56 }