diff options
Diffstat (limited to 'youtube_dl/extractor/shared.py')
-rw-r--r-- | youtube_dl/extractor/shared.py | 31 |
1 files changed, 19 insertions, 12 deletions
diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index 26ced716e..8eda3c864 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -1,31 +1,39 @@ from __future__ import unicode_literals -import re import base64 from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, int_or_none, + sanitized_Request, ) class SharedIE(InfoExtractor): - _VALID_URL = r'http://shared\.sx/(?P<id>[\da-z]{10})' + IE_DESC = 'shared.sx and vivo.sx' + _VALID_URL = r'http://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})' - _TEST = { + _TESTS = [{ 'url': 'http://shared.sx/0060718775', 'md5': '106fefed92a8a2adb8c98e6a0652f49b', 'info_dict': { 'id': '0060718775', 'ext': 'mp4', 'title': 'Bmp4', + 'filesize': 1720110, + }, + }, { + 'url': 'http://vivo.sx/d7ddda0e78', + 'md5': '15b3af41be0b4fe01f4df075c2678b2c', + 'info_dict': { + 'id': 'd7ddda0e78', + 'ext': 'mp4', + 'title': 'Chicken', + 'filesize': 528031, }, - } + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -35,9 +43,8 @@ class SharedIE(InfoExtractor): raise ExtractorError( 'Video %s does not exist' % video_id, expected=True) - download_form = dict(re.findall( - r'<input type="hidden" name="([^"]+)" value="([^"]*)"', webpage)) - request = compat_urllib_request.Request( + download_form = self._hidden_inputs(webpage) + request = sanitized_Request( url, compat_urllib_parse.urlencode(download_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') @@ -47,7 +54,7 @@ class SharedIE(InfoExtractor): video_url = self._html_search_regex( r'data-url="([^"]+)"', video_page, 'video URL') title = base64.b64decode(self._html_search_meta( - 'full:title', webpage, 'title')).decode('utf-8') + '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( |