]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/teamcoco.py
5fa67eb8d4441d62c1591289551171cdbcbcf45b
[youtubedl] / youtube_dl / extractor / teamcoco.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6
7
8 class TeamcocoIE(InfoExtractor):
9 _VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)'
10 _TESTS = [
11 {
12 'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',
13 'file': '80187.mp4',
14 'md5': '3f7746aa0dc86de18df7539903d399ea',
15 'info_dict': {
16 'title': 'Conan Becomes A Mary Kay Beauty Consultant',
17 'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.'
18 }
19 }, {
20 'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
21 'file': '19705.mp4',
22 'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
23 'info_dict': {
24 "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.",
25 "title": "Louis C.K. Interview Pt. 1 11/3/11"
26 }
27 }
28 ]
29
30 def _real_extract(self, url):
31 mobj = re.match(self._VALID_URL, url)
32
33 display_id = mobj.group('display_id')
34 webpage = self._download_webpage(url, display_id)
35
36 video_id = mobj.group("video_id")
37 if not video_id:
38 video_id = self._html_search_regex(
39 r'data-node-id="(\d+?)"',
40 webpage, 'video id')
41
42 data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
43 data = self._download_xml(
44 data_url, display_id, 'Downloading data webpage')
45
46 qualities = ['500k', '480p', '1000k', '720p', '1080p']
47 formats = []
48 for filed in data.findall('files/file'):
49 if filed.attrib.get('playmode') == 'all':
50 # it just duplicates one of the entries
51 break
52 file_url = filed.text
53 m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
54 if m_format is not None:
55 format_id = m_format.group(1)
56 else:
57 format_id = filed.attrib['bitrate']
58 tbr = (
59 int(filed.attrib['bitrate'])
60 if filed.attrib['bitrate'].isdigit()
61 else None)
62
63 try:
64 quality = qualities.index(format_id)
65 except ValueError:
66 quality = -1
67 formats.append({
68 'url': file_url,
69 'ext': 'mp4',
70 'tbr': tbr,
71 'format_id': format_id,
72 'quality': quality,
73 })
74
75 self._sort_formats(formats)
76
77 return {
78 'id': video_id,
79 'display_id': display_id,
80 'formats': formats,
81 'title': self._og_search_title(webpage),
82 'thumbnail': self._og_search_thumbnail(webpage),
83 'description': self._og_search_description(webpage),
84 }