]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tlc.py
Merge tag 'upstream/2014.11.21'
[youtubedl] / youtube_dl / extractor / tlc.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3 import re
4
5 from .common import InfoExtractor
6 from .brightcove import BrightcoveIE
7 from .discovery import DiscoveryIE
8 from ..utils import compat_urlparse
9
10
11 class TlcIE(DiscoveryIE):
12 IE_NAME = 'tlc.com'
13 _VALID_URL = r'http://www\.tlc\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
14
15 _TEST = {
16 'url': 'http://www.tlc.com/tv-shows/cake-boss/videos/too-big-to-fly.htm',
17 'md5': 'c4038f4a9b44d0b5d74caaa64ed2a01a',
18 'info_dict': {
19 'id': '853232',
20 'ext': 'mp4',
21 'title': 'Cake Boss: Too Big to Fly',
22 'description': 'Buddy has taken on a high flying task.',
23 'duration': 119,
24 },
25 }
26
27
28 class TlcDeIE(InfoExtractor):
29 IE_NAME = 'tlc.de'
30 _VALID_URL = r'http://www\.tlc\.de/sendungen/[^/]+/videos/(?P<title>[^/?]+)'
31
32 _TEST = {
33 'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001',
34 'info_dict': {
35 'id': '3235167922001',
36 'ext': 'mp4',
37 'title': 'Breaking Amish: Die Welt da draußen',
38 'uploader': 'Discovery Networks - Germany',
39 'description': 'Vier Amische und eine Mennonitin wagen in New York'
40 ' den Sprung in ein komplett anderes Leben. Begleitet sie auf'
41 ' ihrem spannenden Weg.',
42 },
43 }
44
45 def _real_extract(self, url):
46 mobj = re.match(self._VALID_URL, url)
47 title = mobj.group('title')
48 webpage = self._download_webpage(url, title)
49 iframe_url = self._search_regex(
50 '<iframe src="(http://www\.tlc\.de/wp-content/.+?)"', webpage,
51 'iframe url')
52 # Otherwise we don't get the correct 'BrightcoveExperience' element,
53 # example: http://www.tlc.de/sendungen/cake-boss/videos/cake-boss-cannoli-drama/
54 iframe_url = iframe_url.replace('.htm?', '.php?')
55 url_fragment = compat_urlparse.urlparse(url).fragment
56 if url_fragment:
57 # Since the fragment is not send to the server, we always get the same iframe
58 iframe_url = re.sub(r'playlist=(\d+)', 'playlist=%s' % url_fragment, iframe_url)
59 iframe = self._download_webpage(iframe_url, title)
60
61 return {
62 '_type': 'url',
63 'url': BrightcoveIE._extract_brightcove_url(iframe),
64 'ie': BrightcoveIE.ie_key(),
65 }