diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-07-11 04:17:54 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-07-11 04:17:54 +0600 |
commit | 3f19b9b7c111ef0f12b880d8676a346280cc3ef4 (patch) | |
tree | b885c026800b6955a085710a409a51404e01b97c /youtube_dl | |
parent | 1c0163a5cc1d6b8fa5c7b4ee39b28e6e47c8981c (diff) | |
parent | 2028c6e03d7e254831350081bb4b4741b0b47ac4 (diff) |
Merge branch 'webofstories' of https://github.com/dufferzafar/youtube-dl into dufferzafar-webofstories
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 5 | ||||
-rw-r--r-- | youtube_dl/extractor/webofstories.py | 25 |
2 files changed, 29 insertions, 1 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d886f7d68..22f7c7a75 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -713,7 +713,10 @@ from .wdr import ( WDRMobileIE, WDRMausIE, ) -from .webofstories import WebOfStoriesIE +from .webofstories import ( + WebOfStoriesIE, + WebOfStoriesPlaylistIE, +) from .weibo import WeiboIE from .wimp import WimpIE from .wistia import WistiaIE diff --git a/youtube_dl/extractor/webofstories.py b/youtube_dl/extractor/webofstories.py index 73077a312..d70e30c00 100644 --- a/youtube_dl/extractor/webofstories.py +++ b/youtube_dl/extractor/webofstories.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import int_or_none @@ -98,3 +100,26 @@ class WebOfStoriesIE(InfoExtractor): 'description': description, 'duration': duration, } + + +class WebOfStoriesPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?webofstories\.com/playAll/(?P<id>[^/]+)' + _TESTS = [] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result('http://www.webofstories.com/play/%s' % video_number, 'WebOfStories') + for video_number in set(re.findall('href="/playAll/%s\?sId=(\d+)"' % playlist_id, webpage)) + ] + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*Web\sof\sStories</title>', webpage, 'title') + + description = self._html_search_meta( + 'description', webpage, 'description') + + return self.playlist_result(entries, playlist_id, title, description) |