]>
Commit | Line | Data |
---|---|---|
1 | import re | |
2 | ||
3 | from .common import InfoExtractor | |
4 | from ..compat import ( | |
5 | compat_urllib_parse_unquote, | |
6 | compat_urllib_parse_unquote_plus, | |
7 | ) | |
8 | from ..utils import ( | |
9 | clean_html, | |
10 | ExtractorError, | |
11 | ) | |
12 | ||
13 | ||
14 | class PlayvidIE(InfoExtractor): | |
15 | _VALID_URL = r'https?://(?:www\.)?playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)' | |
16 | _TESTS = [{ | |
17 | 'url': 'http://www.playvid.com/watch/RnmBNgtrrJu', | |
18 | 'md5': 'ffa2f6b2119af359f544388d8c01eb6c', | |
19 | 'info_dict': { | |
20 | 'id': 'RnmBNgtrrJu', | |
21 | 'ext': 'mp4', | |
22 | 'title': 'md5:9256d01c6317e3f703848b5906880dc8', | |
23 | 'duration': 82, | |
24 | 'age_limit': 18, | |
25 | }, | |
26 | 'skip': 'Video removed due to ToS', | |
27 | }, { | |
28 | 'url': 'http://www.playvid.com/watch/hwb0GpNkzgH', | |
29 | 'md5': '39d49df503ad7b8f23a4432cbf046477', | |
30 | 'info_dict': { | |
31 | 'id': 'hwb0GpNkzgH', | |
32 | 'ext': 'mp4', | |
33 | 'title': 'Ellen Euro Cutie Blond Takes a Sexy Survey Get Facial in The Park', | |
34 | 'age_limit': 18, | |
35 | 'thumbnail': r're:^https?://.*\.jpg$', | |
36 | }, | |
37 | }] | |
38 | ||
39 | def _real_extract(self, url): | |
40 | video_id = self._match_id(url) | |
41 | webpage = self._download_webpage(url, video_id) | |
42 | ||
43 | m_error = re.search( | |
44 | r'<div class="block-error">\s*<div class="heading">\s*<div>(?P<msg>.+?)</div>\s*</div>', webpage) | |
45 | if m_error: | |
46 | raise ExtractorError(clean_html(m_error.group('msg')), expected=True) | |
47 | ||
48 | video_title = None | |
49 | duration = None | |
50 | video_thumbnail = None | |
51 | formats = [] | |
52 | ||
53 | # most of the information is stored in the flashvars | |
54 | flashvars = self._html_search_regex( | |
55 | r'flashvars="(.+?)"', webpage, 'flashvars') | |
56 | ||
57 | infos = compat_urllib_parse_unquote(flashvars).split(r'&') | |
58 | for info in infos: | |
59 | videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info) | |
60 | if videovars_match: | |
61 | key = videovars_match.group(1) | |
62 | val = videovars_match.group(2) | |
63 | ||
64 | if key == 'title': | |
65 | video_title = compat_urllib_parse_unquote_plus(val) | |
66 | if key == 'duration': | |
67 | try: | |
68 | duration = int(val) | |
69 | except ValueError: | |
70 | pass | |
71 | if key == 'big_thumb': | |
72 | video_thumbnail = val | |
73 | ||
74 | videourl_match = re.match( | |
75 | r'^video_urls\]\[(?P<resolution>[0-9]+)p', key) | |
76 | if videourl_match: | |
77 | height = int(videourl_match.group('resolution')) | |
78 | formats.append({ | |
79 | 'height': height, | |
80 | 'url': val, | |
81 | }) | |
82 | self._sort_formats(formats) | |
83 | ||
84 | # Extract title - should be in the flashvars; if not, look elsewhere | |
85 | if video_title is None: | |
86 | video_title = self._html_extract_title(webpage) | |
87 | ||
88 | return { | |
89 | 'id': video_id, | |
90 | 'formats': formats, | |
91 | 'title': video_title, | |
92 | 'thumbnail': video_thumbnail, | |
93 | 'duration': duration, | |
94 | 'description': None, | |
95 | 'age_limit': 18 | |
96 | } |