diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-02-06 03:23:42 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-02-06 03:23:42 +0600 |
commit | 9c91a8fa70e3c2f29dd23809e90b3357b6c1cdc4 (patch) | |
tree | 24e9924e1c9c42be34961aa8a7e20ec32ea59333 | |
parent | 41469f335e7ead11821b5b02cf8b1556be2247a5 (diff) |
[tweakers] Switch extraction to xspf playlist, extract all formats and meta (#4881)
-rw-r--r-- | youtube_dl/extractor/tweakers.py | 58 |
1 files changed, 44 insertions, 14 deletions
diff --git a/youtube_dl/extractor/tweakers.py b/youtube_dl/extractor/tweakers.py index e332d4694..c80ec15cf 100644 --- a/youtube_dl/extractor/tweakers.py +++ b/youtube_dl/extractor/tweakers.py @@ -1,35 +1,65 @@ -# coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..utils import ( + xpath_text, + xpath_with_ns, + int_or_none, + float_or_none, +) class TweakersIE(InfoExtractor): - _VALID_URL = r'https?://tweakers\.net/video/(?P<id>[0-9]+).*' + _VALID_URL = r'https?://tweakers\.net/video/(?P<id>\d+)' _TEST = { 'url': 'https://tweakers.net/video/9926/new-nintendo-3ds-xl-op-alle-fronten-beter.html', - 'md5': 'f7f7f3027166a7f32f024b4ae6571ced', + 'md5': '1b5afa817403bb5baa08359dca31e6df', 'info_dict': { 'id': '9926', 'ext': 'mp4', - 'title': 'New-Nintendo-3Ds-Xl-Op-Alle-Fronten-Beter', + 'title': 'New Nintendo 3DS XL - Op alle fronten beter', + 'description': 'md5:f97324cc71e86e11c853f0763820e3ba', + 'thumbnail': 're:^https?://.*\.jpe?g$', + 'duration': 386, } } 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) + + playlist = self._download_xml( + 'https://tweakers.net/video/s1playlist/%s/playlist.xspf' % video_id, + video_id) + + NS_MAP = { + 'xspf': 'http://xspf.org/ns/0/', + 's1': 'http://static.streamone.nl/player/ns/0', + } + + track = playlist.find(xpath_with_ns('./xspf:trackList/xspf:track', NS_MAP)) + + title = xpath_text( + track, xpath_with_ns('./xspf:title', NS_MAP), 'title') + description = xpath_text( + track, xpath_with_ns('./xspf:annotation', NS_MAP), 'description') + thumbnail = xpath_text( + track, xpath_with_ns('./xspf:image', NS_MAP), 'thumbnail') + duration = float_or_none( + xpath_text(track, xpath_with_ns('./xspf:duration', NS_MAP), 'duration'), + 1000) + + formats = [{ + 'url': location.text, + 'format_id': location.get(xpath_with_ns('s1:label', NS_MAP)), + 'width': int_or_none(location.get(xpath_with_ns('s1:width', NS_MAP))), + 'height': int_or_none(location.get(xpath_with_ns('s1:height', NS_MAP))), + } for location in track.findall(xpath_with_ns('./xspf:location', NS_MAP))] return { 'id': video_id, - 'ext': 'mp4', 'title': title, - 'url': re.findall('http.*mp4', player_page)[0], + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, } |