]>
Commit | Line | Data |
---|---|---|
aec74dd9 | 1 | import re |
add96eb9 | 2 | import urllib.parse |
aec74dd9 PH |
3 | |
4 | from .common import InfoExtractor | |
1cc79574 | 5 | from ..utils import ( |
59c03a9b | 6 | ExtractorError, |
aec74dd9 | 7 | parse_duration, |
e2dbcaa1 | 8 | remove_end, |
aec74dd9 PH |
9 | ) |
10 | ||
11 | ||
12 | class VuClipIE(InfoExtractor): | |
5886b38d | 13 | _VALID_URL = r'https?://(?:m\.)?vuclip\.com/w\?.*?cid=(?P<id>[0-9]+)' |
aec74dd9 PH |
14 | |
15 | _TEST = { | |
ecc90093 | 16 | 'url': 'http://m.vuclip.com/w?cid=1129900602&bu=8589892792&frm=w&z=34801&op=0&oc=843169247§ion=recommend', |
aec74dd9 | 17 | 'info_dict': { |
ecc90093 | 18 | 'id': '1129900602', |
aec74dd9 | 19 | 'ext': '3gp', |
ecc90093 YCH |
20 | 'title': 'Top 10 TV Convicts', |
21 | 'duration': 733, | |
add96eb9 | 22 | }, |
aec74dd9 PH |
23 | } |
24 | ||
25 | def _real_extract(self, url): | |
1cc79574 | 26 | video_id = self._match_id(url) |
a7a747d6 | 27 | webpage = self._download_webpage(url, video_id) |
1cc79574 | 28 | |
aec74dd9 PH |
29 | ad_m = re.search( |
30 | r'''value="No.*?" onClick="location.href='([^"']+)'"''', webpage) | |
31 | if ad_m: | |
add96eb9 | 32 | urlr = urllib.parse.urlparse(url) |
aec74dd9 PH |
33 | adfree_url = urlr.scheme + '://' + urlr.netloc + ad_m.group(1) |
34 | webpage = self._download_webpage( | |
35 | adfree_url, video_id, note='Download post-ad page') | |
36 | ||
59c03a9b PH |
37 | error_msg = self._html_search_regex( |
38 | r'<p class="message">(.*?)</p>', webpage, 'error message', | |
39 | default=None) | |
40 | if error_msg: | |
41 | raise ExtractorError( | |
add96eb9 | 42 | f'{self.IE_NAME} said: {error_msg}', expected=True) |
59c03a9b PH |
43 | |
44 | # These clowns alternate between two page types | |
e2dbcaa1 YCH |
45 | video_url = self._search_regex( |
46 | r'<a[^>]+href="([^"]+)"[^>]*><img[^>]+src="[^"]*/play\.gif', | |
47 | webpage, 'video URL', default=None) | |
48 | if video_url: | |
49 | formats = [{ | |
50 | 'url': video_url, | |
51 | }] | |
52 | else: | |
ecc90093 | 53 | formats = self._parse_html5_media_entries(url, webpage, video_id)[0]['formats'] |
aec74dd9 | 54 | |
e2dbcaa1 YCH |
55 | title = remove_end(self._html_search_regex( |
56 | r'<title>(.*?)-\s*Vuclip</title>', webpage, 'title').strip(), ' - Video') | |
aec74dd9 | 57 | |
e2dbcaa1 YCH |
58 | duration = parse_duration(self._html_search_regex( |
59 | r'[(>]([0-9]+:[0-9]+)(?:<span|\))', webpage, 'duration', fatal=False)) | |
aec74dd9 PH |
60 | |
61 | return { | |
62 | 'id': video_id, | |
63 | 'formats': formats, | |
64 | 'title': title, | |
65 | 'duration': duration, | |
66 | } |