[tweakers] Switch extraction to xspf playlist, extract all formats and meta (#4881)

This commit is contained in:
Sergey M․ 2015-02-06 03:23:42 +06:00
parent 41469f335e
commit 9c91a8fa70

View file

@ -1,35 +1,65 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
xpath_text,
xpath_with_ns,
int_or_none,
float_or_none,
)
class TweakersIE(InfoExtractor): 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 = { _TEST = {
'url': 'https://tweakers.net/video/9926/new-nintendo-3ds-xl-op-alle-fronten-beter.html', 'url': 'https://tweakers.net/video/9926/new-nintendo-3ds-xl-op-alle-fronten-beter.html',
'md5': 'f7f7f3027166a7f32f024b4ae6571ced', 'md5': '1b5afa817403bb5baa08359dca31e6df',
'info_dict': { 'info_dict': {
'id': '9926', 'id': '9926',
'ext': 'mp4', '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): 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) 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 playlist = self._download_xml(
player_url = '/'.join(splitted_url) + '.html' 'https://tweakers.net/video/s1playlist/%s/playlist.xspf' % video_id,
player_page = self._download_webpage(player_url, 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 { return {
'id': video_id, 'id': video_id,
'ext': 'mp4',
'title': title, 'title': title,
'url': re.findall('http.*mp4', player_page)[0], 'description': description,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
} }