[tweakers] fix info extraction(closes #9516)

This commit is contained in:
Remita Amine 2016-07-07 12:49:02 +01:00
parent 571808a7aa
commit 5f87d845eb
1 changed files with 43 additions and 6 deletions

View File

@ -1,25 +1,62 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
determine_ext,
mimetype2ext,
)
class TweakersIE(InfoExtractor):
_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': '3147e4ddad366f97476a93863e4557c8',
'md5': 'fe73e417c093a788e0160c4025f88b15',
'info_dict': {
'id': '9926',
'ext': 'mp4',
'title': 'New Nintendo 3DS XL - Op alle fronten beter',
'description': 'md5:f97324cc71e86e11c853f0763820e3ba',
'description': 'md5:3789b21fed9c0219e9bcaacd43fab280',
'thumbnail': 're:^https?://.*\.jpe?g$',
'duration': 386,
'uploader_id': 's7JeEm',
}
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
entries = self._extract_xspf_playlist(
'https://tweakers.net/video/s1playlist/%s/playlist.xspf' % playlist_id, playlist_id)
return self.playlist_result(entries, playlist_id)
video_id = self._match_id(url)
video_data = self._download_json(
'https://tweakers.net/video/s1playlist/%s/1920/1080/playlist.json' % video_id,
video_id)['items'][0]
title = video_data['title']
formats = []
for location in video_data.get('locations', {}).get('progressive', []):
format_id = location.get('label')
width = int_or_none(location.get('width'))
height = int_or_none(location.get('height'))
for source in location.get('sources', []):
source_url = source.get('src')
if not source_url:
continue
ext = mimetype2ext(source.get('type')) or determine_ext(source_url)
formats.append({
'format_id': format_id,
'url': source_url,
'width': width,
'height': height,
'ext': ext,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('poster'),
'duration': int_or_none(video_data.get('duration')),
'uploader_id': video_data.get('account'),
'formats': formats,
}