From: robin Date: Thu, 5 Feb 2015 18:55:41 +0000 (+0100) Subject: [tweakers] Add new extractor X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=e3aaace4005e7b767d28152e60d1cf6272c398ec;p=youtube-dl [tweakers] Add new extractor --- 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..3080f9e46 --- /dev/null +++ b/youtube_dl/extractor/tweakers.py @@ -0,0 +1,41 @@ +# 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[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', + # TODO more properties, either as: + # * A value + # * MD5 checksum; start the string with md5: + # * A regular expression; start the string with re: + # * Any Python type (for example int or float) + } + } + + def _real_extract(self, url): + splitted_url = re.split('.html|/', url) + del splitted_url[-1] # To remove extra '/' at the end + video_id = splitted_url[4] + 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], + 'player_url': player_url + }