diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2014-09-18 18:54:03 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2014-09-18 18:54:03 +0200 |
commit | 0529eef5a4513d8f3c042f09fe5485e1c41e2f08 (patch) | |
tree | 0fe2de0fe18e25b15d9a5ff5b983c5bc6e30eb7f /youtube_dl/extractor/hypestat.py | |
parent | fd78a4d3e63f191e0774584d9b71bf25a2d8dbcf (diff) | |
download | youtube-dl-0529eef5a4513d8f3c042f09fe5485e1c41e2f08.tar.xz |
[hypestat] Unify allmyvideos and vidspot (Closes #3788)
Diffstat (limited to 'youtube_dl/extractor/hypestat.py')
-rw-r--r-- | youtube_dl/extractor/hypestat.py | 67 |
1 files changed, 67 insertions, 0 deletions
diff --git a/youtube_dl/extractor/hypestat.py b/youtube_dl/extractor/hypestat.py new file mode 100644 index 000000000..8b8db30ae --- /dev/null +++ b/youtube_dl/extractor/hypestat.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import os.path +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, +) + + +class HypestatIE(InfoExtractor): + IE_DESC = 'allmyvideos.net and vidspot.net' + _VALID_URL = r'https?://(?:allmyvideos|vidspot)\.net/(?P<id>[a-zA-Z0-9_-]+)' + + _TESTS = [{ + 'url': 'http://allmyvideos.net/jih3nce3x6wn', + 'md5': '710883dee1bfc370ecf9fa6a89307c88', + 'info_dict': { + 'id': 'jih3nce3x6wn', + 'ext': 'mp4', + 'title': 'youtube-dl test video', + }, + }, { + 'url': 'http://vidspot.net/l2ngsmhs8ci5', + 'md5': '710883dee1bfc370ecf9fa6a89307c88', + 'info_dict': { + 'id': 'l2ngsmhs8ci5', + 'ext': 'mp4', + 'title': 'youtube-dl test video', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + orig_webpage = self._download_webpage(url, video_id) + fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage) + data = dict(fields) + + post = compat_urllib_parse.urlencode(data) + headers = { + b'Content-Type': b'application/x-www-form-urlencoded', + } + req = compat_urllib_request.Request(url, post, headers) + webpage = self._download_webpage( + req, video_id, note='Downloading video page ...') + + title = os.path.splitext(data['fname'])[0] + + #Could be several links with different quality + links = re.findall(r'"file" : "?(.+?)",', webpage) + # Assume the links are ordered in quality + formats = [{ + 'url': l, + 'quality': i, + } for i, l in enumerate(links)] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + } |