]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xfileshare.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
17 class XFileShareIE(InfoExtractor
):
19 (r
'daclips\.(?:in|com)', 'DaClips'),
20 (r
'filehoot\.com', 'FileHoot'),
21 (r
'gorillavid\.(?:in|com)', 'GorillaVid'),
22 (r
'movpod\.in', 'MovPod'),
23 (r
'powerwatch\.pw', 'PowerWatch'),
24 (r
'rapidvideo\.ws', 'Rapidvideo.ws'),
25 (r
'thevideobee\.to', 'TheVideoBee'),
26 (r
'vidto\.me', 'Vidto'),
27 (r
'streamin\.to', 'Streamin.To'),
28 (r
'xvidstage\.com', 'XVIDSTAGE'),
29 (r
'vidabc\.com', 'Vid ABC'),
30 (r
'vidbom\.com', 'VidBom'),
31 (r
'vidlo\.us', 'vidlo'),
32 (r
'rapidvideo\.(?:cool|org)', 'RapidVideo.TV'),
33 (r
'fastvideo\.me', 'FastVideo.me'),
36 IE_DESC
= 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES
))[1])
37 _VALID_URL
= (r
'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
38 % '|'.join(site
for site
in list(zip(*_SITES
))[0]))
40 _FILE_NOT_FOUND_REGEXES
= (
41 r
'>(?:404 - )?File Not Found<',
42 r
'>The file was removed by administrator<',
46 'url': 'http://gorillavid.in/06y9juieqpmi',
47 'md5': '5ae4a3580620380619678ee4875893ba',
51 'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
52 'thumbnail': r
're:http://.*\.jpg',
55 'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
56 'only_matching': True,
58 'url': 'http://daclips.in/3rso4kdn6f9m',
59 'md5': '1ad8fd39bb976eeb66004d3a4895f106',
63 'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
64 'thumbnail': r
're:http://.*\.jpg',
67 'url': 'http://movpod.in/0wguyyxi1yca',
68 'only_matching': True,
70 'url': 'http://filehoot.com/3ivfabn7573c.html',
74 'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
75 'thumbnail': r
're:http://.*\.jpg',
77 'skip': 'Video removed',
79 'url': 'http://vidto.me/ku5glz52nqe1.html',
86 'url': 'http://powerwatch.pw/duecjibvicbu',
90 'title': 'Big Buck Bunny trailer',
93 'url': 'http://xvidstage.com/e0qcnl03co6z',
97 'title': 'Chucky Prank 2015.mp4',
100 # removed by administrator
101 'url': 'http://xvidstage.com/amfy7atlkx25',
102 'only_matching': True,
104 'url': 'http://vidabc.com/i8ybqscrphfv',
106 'id': 'i8ybqscrphfv',
108 'title': 're:Beauty and the Beast 2017',
111 'skip_download': True,
114 'url': 'http://www.rapidvideo.cool/b667kprndr8w',
115 'only_matching': True,
117 'url': 'http://www.fastvideo.me/k8604r8nk8sn/FAST_FURIOUS_8_-_Trailer_italiano_ufficiale.mp4.html',
118 'only_matching': True
122 def _extract_urls(webpage
):
125 for mobj
in re
.finditer(
126 r
'<iframe\b[^>]+\bsrc=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:%s)/embed
-[0-9a
-zA
-Z
]+.*?
)\
1'
127 % '|
'.join(site for site in list(zip(*XFileShareIE._SITES))[0]),
130 def _real_extract(self, url):
131 mobj = re.match(self._VALID_URL, url)
132 video_id = mobj.group('id')
134 url = 'http
://%s/%s' % (mobj.group('host
'), video_id)
135 webpage = self._download_webpage(url, video_id)
137 if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
138 raise ExtractorError('Video
%s does
not exist
' % video_id, expected=True)
140 fields = self._hidden_inputs(webpage)
142 if fields['op
'] == 'download1
':
143 countdown = int_or_none(self._search_regex(
144 r'<span
id="countdown_str">(?
:[Ww
]ait
)?\s
*<span
id="cxc">(\d
+)</span
>\s
*(?
:seconds?
)?
</span
>',
145 webpage, 'countdown
', default=None))
147 self._sleep(countdown, video_id)
149 webpage = self._download_webpage(
150 url, video_id, 'Downloading video page
',
151 data=urlencode_postdata(fields), headers={
153 'Content
-type': 'application
/x
-www
-form
-urlencoded
',
156 title = (self._search_regex(
157 (r'style
="z-index: [0-9]+;">([^
<]+)</span
>',
158 r'<td nowrap
>([^
<]+)</td
>',
159 r'h4
-fine
[^
>]*>([^
<]+)<',
161 r'<h2
class="video-page-head">([^
<]+)</h2
>',
162 r'<h2 style
="[^"]*color
:#403f3d[^"]*"[^>]*>([^<]+)<'), # streamin.to
163 webpage
, 'title', default
=None) or self
._og
_search
_title
(
164 webpage
, default
=None) or video_id
).strip()
166 def extract_formats(default
=NO_DEFAULT
):
169 r
'(?:file|src)\s*:\s*(["\'])(?P
<url
>http(?
:(?
!\
1).)+\
.(?
:m3u8|mp4|flv
)(?
:(?
!\
1).)*)\
1',
170 r'file_link\s
*=\s
*(["\'])(?P<url>http(?:(?!\1).)+)\1',
171 r'addVariable\((\\?["\'])file\
1\s
*,\s
*(\\?
["\'])(?P<url>http(?:(?!\2).)+)\2\)',
172 r'<embed[^>]+src=(["\'])(?P
<url
>http(?
:(?
!\
1).)+\
.(?
:m3u8|mp4|flv
)(?
:(?
!\
1).)*)\
1'):
173 for mobj in re.finditer(regex, webpage):
174 video_url = mobj.group('url
')
175 if video_url not in urls:
176 urls.append(video_url)
178 for video_url in urls:
179 if determine_ext(video_url) == 'm3u8
':
180 formats.extend(self._extract_m3u8_formats(
181 video_url, video_id, 'mp4
',
182 entry_protocol='m3u8_native
', m3u8_id='hls
',
189 if not formats and default is not NO_DEFAULT:
191 self._sort_formats(formats)
194 formats = extract_formats(default=None)
197 webpage = decode_packed_codes(self._search_regex(
198 r"(}\('(.+)',(\d+),(\d+),'[^
']*\b(?:file|embed)\b[^']*'\.split\('\|
'\))",
199 webpage, 'packed code
'))
200 formats = extract_formats()
202 thumbnail = self._search_regex(
203 r'image\s
*:\s
*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
208 'thumbnail': thumbnail,