]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/playvid.py
Initiate a new release.
[youtubedl] / youtube_dl / extractor / playvid.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..compat import (
7 compat_urllib_parse,
8 )
9 from ..utils import (
10 clean_html,
11 ExtractorError,
12 )
13
14
15 class PlayvidIE(InfoExtractor):
16 _VALID_URL = r'https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
17 _TEST = {
18 'url': 'http://www.playvid.com/watch/RnmBNgtrrJu',
19 'md5': 'ffa2f6b2119af359f544388d8c01eb6c',
20 'info_dict': {
21 'id': 'RnmBNgtrrJu',
22 'ext': 'mp4',
23 'title': 'md5:9256d01c6317e3f703848b5906880dc8',
24 'duration': 82,
25 'age_limit': 18,
26 }
27 }
28
29 def _real_extract(self, url):
30 video_id = self._match_id(url)
31 webpage = self._download_webpage(url, video_id)
32
33 m_error = re.search(
34 r'<div class="block-error">\s*<div class="heading">\s*<div>(?P<msg>.+?)</div>\s*</div>', webpage)
35 if m_error:
36 raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
37
38 video_title = None
39 duration = None
40 video_thumbnail = None
41 formats = []
42
43 # most of the information is stored in the flashvars
44 flashvars = self._html_search_regex(
45 r'flashvars="(.+?)"', webpage, 'flashvars')
46
47 infos = compat_urllib_parse.unquote(flashvars).split(r'&')
48 for info in infos:
49 videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
50 if videovars_match:
51 key = videovars_match.group(1)
52 val = videovars_match.group(2)
53
54 if key == 'title':
55 video_title = compat_urllib_parse.unquote_plus(val)
56 if key == 'duration':
57 try:
58 duration = int(val)
59 except ValueError:
60 pass
61 if key == 'big_thumb':
62 video_thumbnail = val
63
64 videourl_match = re.match(
65 r'^video_urls\]\[(?P<resolution>[0-9]+)p', key)
66 if videourl_match:
67 height = int(videourl_match.group('resolution'))
68 formats.append({
69 'height': height,
70 'url': val,
71 })
72 self._sort_formats(formats)
73
74 # Extract title - should be in the flashvars; if not, look elsewhere
75 if video_title is None:
76 video_title = self._html_search_regex(
77 r'<title>(.*?)</title', webpage, 'title')
78
79 return {
80 'id': video_id,
81 'formats': formats,
82 'title': video_title,
83 'thumbnail': video_thumbnail,
84 'duration': duration,
85 'description': None,
86 'age_limit': 18
87 }