diff options
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/vodlocker.py | 66 |
2 files changed, 67 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 12cca5c2e..7b3f9ae24 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -342,6 +342,7 @@ from .vine import ( ) from .viki import VikiIE from .vk import VKIE +from .vodlocker import VodlockerIE from .vube import VubeIE from .vuclip import VuClipIE from .vulture import VultureIE diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py new file mode 100644 index 000000000..fdab0e7bf --- /dev/null +++ b/youtube_dl/extractor/vodlocker.py @@ -0,0 +1,66 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re +import time +from .common import InfoExtractor +from ..utils import ( + determine_ext, + compat_urllib_parse, + compat_urllib_request, +) + + +class VodlockerIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vodlocker.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?' + + _TESTS = [{ + 'url': 'http://vodlocker.com/e8wvyzz4sl42', + 'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf', + 'info_dict': { + 'id': 'e8wvyzz4sl42', + 'ext': 'mp4', + 'title': 'Germany vs Brazil', + 'thumbnail': 're:http://.*\.jpg', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://vodlocker.com/%s' % video_id + + webpage = self._download_webpage(url, video_id) + + fields = dict(re.findall(r'''(?x)<input\s+ + type="hidden"\s+ + name="([^"]+)"\s+ + (?:id="[^"]+"\s+)? + value="([^"]*)" + ''', webpage)) + + if fields['op'] == 'download1': + time.sleep(3) #they do detect when requests happen too fast! + post = compat_urllib_parse.urlencode(fields) + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + webpage = self._download_webpage(req, video_id, 'Downloading video page') + + title = self._search_regex(r'id="file_title".*?>\s*(.*?)\s*<span', webpage, 'title') + thumbnail = self._search_regex(r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail') + url = self._search_regex(r'file:\s*"(http[^\"]+)",', webpage, 'file url') + + formats = [{ + 'format_id': 'sd', + 'url': url, + 'ext': determine_ext(url), + 'quality': 1, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } |