]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/teamcoco.py
Update changelog.
[youtubedl] / youtube_dl / extractor / teamcoco.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 ExtractorError,
8 )
9
10
11 class TeamcocoIE(InfoExtractor):
12 _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
13 _TEST = {
14 'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
15 'file': '19705.mp4',
16 'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
17 'info_dict': {
18 "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.",
19 "title": "Louis C.K. Interview Pt. 1 11/3/11"
20 }
21 }
22
23 def _real_extract(self, url):
24 mobj = re.match(self._VALID_URL, url)
25 if mobj is None:
26 raise ExtractorError('Invalid URL: %s' % url)
27 url_title = mobj.group('url_title')
28 webpage = self._download_webpage(url, url_title)
29
30 video_id = self._html_search_regex(
31 r'<article class="video" data-id="(\d+?)"',
32 webpage, 'video id')
33
34 self.report_extraction(video_id)
35
36 data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
37 data = self._download_xml(data_url, video_id, 'Downloading data webpage')
38
39 qualities = ['500k', '480p', '1000k', '720p', '1080p']
40 formats = []
41 for filed in data.findall('files/file'):
42 if filed.attrib.get('playmode') == 'all':
43 # it just duplicates one of the entries
44 break
45 file_url = filed.text
46 m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
47 if m_format is not None:
48 format_id = m_format.group(1)
49 else:
50 format_id = filed.attrib['bitrate']
51 tbr = (
52 int(filed.attrib['bitrate'])
53 if filed.attrib['bitrate'].isdigit()
54 else None)
55
56 try:
57 quality = qualities.index(format_id)
58 except ValueError:
59 quality = -1
60 formats.append({
61 'url': file_url,
62 'ext': 'mp4',
63 'tbr': tbr,
64 'format_id': format_id,
65 'quality': quality,
66 })
67
68 self._sort_formats(formats)
69
70 return {
71 'id': video_id,
72 'formats': formats,
73 'title': self._og_search_title(webpage),
74 'thumbnail': self._og_search_thumbnail(webpage),
75 'description': self._og_search_description(webpage),
76 }