[vivo] Fix extraction (closes #11003)

pull/11005/head
Sergey M․ 2016-10-23 18:07:56 +07:00
parent 9aa929d337
commit 9dc13a6780
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
2 changed files with 70 additions and 45 deletions

View File

@ -796,7 +796,10 @@ from .sendtonews import SendtoNewsIE
from .servingsys import ServingSysIE from .servingsys import ServingSysIE
from .sexu import SexuIE from .sexu import SexuIE
from .shahid import ShahidIE from .shahid import ShahidIE
from .shared import SharedIE from .shared import (
SharedIE,
VivoIE,
)
from .sharesix import ShareSixIE from .sharesix import ShareSixIE
from .sina import SinaIE from .sina import SinaIE
from .sixplay import SixPlayIE from .sixplay import SixPlayIE

View File

@ -10,11 +10,38 @@ from ..utils import (
) )
class SharedIE(InfoExtractor): class SharedBaseIE(InfoExtractor):
IE_DESC = 'shared.sx and vivo.sx' def _real_extract(self, url):
_VALID_URL = r'https?://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})' video_id = self._match_id(url)
_TESTS = [{ webpage, urlh = self._download_webpage_handle(url, video_id)
if self._FILE_NOT_FOUND in webpage:
raise ExtractorError(
'Video %s does not exist' % video_id, expected=True)
video_url = self._extract_video_url(webpage, video_id, url)
title = base64.b64decode(self._html_search_meta(
'full:title', webpage, 'title').encode('utf-8')).decode('utf-8')
filesize = int_or_none(self._html_search_meta(
'full:size', webpage, 'file size', fatal=False))
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'filesize': filesize,
'title': title,
}
class SharedIE(SharedBaseIE):
IE_DESC = 'shared.sx'
_VALID_URL = r'https?://shared\.sx/(?P<id>[\da-z]{10})'
_FILE_NOT_FOUND = '>File does not exist<'
_TEST = {
'url': 'http://shared.sx/0060718775', 'url': 'http://shared.sx/0060718775',
'md5': '106fefed92a8a2adb8c98e6a0652f49b', 'md5': '106fefed92a8a2adb8c98e6a0652f49b',
'info_dict': { 'info_dict': {
@ -23,7 +50,32 @@ class SharedIE(InfoExtractor):
'title': 'Bmp4', 'title': 'Bmp4',
'filesize': 1720110, 'filesize': 1720110,
}, },
}, { }
def _extract_video_url(self, webpage, video_id, url):
download_form = self._hidden_inputs(webpage)
video_page = self._download_webpage(
url, video_id, 'Downloading video page',
data=urlencode_postdata(download_form),
headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': url,
})
video_url = self._html_search_regex(
r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
video_page, 'video URL', group='url')
return video_url
class VivoIE(SharedBaseIE):
IE_DESC = 'vivo.sx'
_VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})'
_FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'
_TEST = {
'url': 'http://vivo.sx/d7ddda0e78', 'url': 'http://vivo.sx/d7ddda0e78',
'md5': '15b3af41be0b4fe01f4df075c2678b2c', 'md5': '15b3af41be0b4fe01f4df075c2678b2c',
'info_dict': { 'info_dict': {
@ -32,43 +84,13 @@ class SharedIE(InfoExtractor):
'title': 'Chicken', 'title': 'Chicken',
'filesize': 528031, 'filesize': 528031,
}, },
}] }
def _real_extract(self, url): def _extract_video_url(self, webpage, video_id, *args):
video_id = self._match_id(url) return self._parse_json(
self._search_regex(
webpage, urlh = self._download_webpage_handle(url, video_id) r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'stream', group='url'),
if '>File does not exist<' in webpage: video_id,
raise ExtractorError( transform_source=lambda x: base64.b64decode(
'Video %s does not exist' % video_id, expected=True) x.encode('ascii')).decode('utf-8'))[0]
download_form = self._hidden_inputs(webpage)
video_page = self._download_webpage(
urlh.geturl(), video_id, 'Downloading video page',
data=urlencode_postdata(download_form),
headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': urlh.geturl(),
})
video_url = self._html_search_regex(
r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
video_page, 'video URL', group='url')
title = base64.b64decode(self._html_search_meta(
'full:title', webpage, 'title').encode('utf-8')).decode('utf-8')
filesize = int_or_none(self._html_search_meta(
'full:size', webpage, 'file size', fatal=False))
thumbnail = self._html_search_regex(
r'data-poster=(["\'])(?P<url>(?:(?!\1).)+)\1',
video_page, 'thumbnail', default=None, group='url')
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'filesize': filesize,
'title': title,
'thumbnail': thumbnail,
}