From 4fb40d6e38e262237459ca69aa3ec8bd3cde6d5a Mon Sep 17 00:00:00 2001 From: Carlos Ramos Date: Thu, 18 Sep 2014 04:24:33 +0200 Subject: [PATCH 1/2] [vidspot] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/vidspot.py | 58 ++++++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+) create mode 100644 youtube_dl/extractor/vidspot.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 75831b40a..b431d57b7 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -398,6 +398,7 @@ from .videopremium import VideoPremiumIE from .videott import VideoTtIE from .videoweed import VideoWeedIE from .vidme import VidmeIE +from .vidspot import VidspotIE from .vimeo import ( VimeoIE, VimeoChannelIE, diff --git a/youtube_dl/extractor/vidspot.py b/youtube_dl/extractor/vidspot.py new file mode 100644 index 000000000..6a2d8787c --- /dev/null +++ b/youtube_dl/extractor/vidspot.py @@ -0,0 +1,58 @@ +from __future__ import unicode_literals + +import os.path +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, +) + + +class VidspotIE(InfoExtractor): + IE_NAME = 'vidspot.net' + _VALID_URL = r'https?://vidspot\.net/(?P[a-zA-Z0-9_-]+)' + + _TEST = { + '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, + } From aa7ef04993a48ccdd7eede4093f0588d1a7d5bf7 Mon Sep 17 00:00:00 2001 From: Carlos Ramos Date: Thu, 18 Sep 2014 05:56:02 +0200 Subject: [PATCH 2/2] Add coding utf-8 --- youtube_dl/extractor/vidspot.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/vidspot.py b/youtube_dl/extractor/vidspot.py index 6a2d8787c..e7279e7f0 100644 --- a/youtube_dl/extractor/vidspot.py +++ b/youtube_dl/extractor/vidspot.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import os.path