diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-02-06 02:59:33 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-02-06 02:59:33 +0600 |
commit | 41469f335e7ead11821b5b02cf8b1556be2247a5 (patch) | |
tree | b536d8d0001aef33b996c6860d97c24957c71b4e /youtube_dl/extractor | |
parent | 300753a0695c17979d6ac42147cb162ff0eedea5 (diff) | |
parent | 67ce4f8820f94961c9b094f9c652f421c9d9f6fb (diff) |
Merge branch 'tweakers' of https://github.com/robin007bond/youtube-dl into robin007bond-tweakers
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/tweakers.py | 35 |
2 files changed, 36 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5866a7617..047f7002a 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -475,6 +475,7 @@ from .tutv import TutvIE from .tvigle import TvigleIE from .tvp import TvpIE, TvpSeriesIE from .tvplay import TVPlayIE +from .tweakers import TweakersIE from .twentyfourvideo import TwentyFourVideoIE from .twitch import ( TwitchVideoIE, diff --git a/youtube_dl/extractor/tweakers.py b/youtube_dl/extractor/tweakers.py new file mode 100644 index 000000000..e332d4694 --- /dev/null +++ b/youtube_dl/extractor/tweakers.py @@ -0,0 +1,35 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class TweakersIE(InfoExtractor): + _VALID_URL = r'https?://tweakers\.net/video/(?P<id>[0-9]+).*' + _TEST = { + 'url': 'https://tweakers.net/video/9926/new-nintendo-3ds-xl-op-alle-fronten-beter.html', + 'md5': 'f7f7f3027166a7f32f024b4ae6571ced', + 'info_dict': { + 'id': '9926', + 'ext': 'mp4', + 'title': 'New-Nintendo-3Ds-Xl-Op-Alle-Fronten-Beter', + } + } + + def _real_extract(self, url): + splitted_url = re.split('.html|/', url) + del splitted_url[-1] # To remove extra '/' at the end + video_id = self._match_id(url) + title = splitted_url[5].title() # Retrieve title for URL and capitalize + splitted_url[3] = splitted_url[3] + '/player' # Add /player to get the player page + player_url = '/'.join(splitted_url) + '.html' + player_page = self._download_webpage(player_url, video_id) + + return { + 'id': video_id, + 'ext': 'mp4', + 'title': title, + 'url': re.findall('http.*mp4', player_page)[0], + } |