youtube-dl/youtube_dl/extractor/viddler.py

139 lines
4.8 KiB
Python
Raw Permalink Normal View History

2014-10-24 22:10:11 +00:00
from __future__ import unicode_literals
2019-03-11 14:53:44 +00:00
import re
from .common import InfoExtractor
2014-10-24 22:10:11 +00:00
from ..utils import (
float_or_none,
int_or_none,
)
class ViddlerIE(InfoExtractor):
2019-03-11 14:53:44 +00:00
_VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)(?:.+?\bsecret=(\d+))?'
_TESTS = [{
2015-01-28 16:49:42 +00:00
'url': 'http://www.viddler.com/v/43903784',
2016-02-09 19:12:47 +00:00
'md5': '9eee21161d2c7f5b39690c3e325fab2f',
2014-10-24 22:10:11 +00:00
'info_dict': {
'id': '43903784',
2016-02-09 19:12:47 +00:00
'ext': 'mov',
2015-01-28 16:49:42 +00:00
'title': 'Video Made Easy',
'description': 'md5:6a697ebd844ff3093bd2e82c37b409cd',
'uploader': 'viddler',
2014-10-24 22:10:11 +00:00
'timestamp': 1335371429,
'upload_date': '20120425',
2015-01-28 16:49:42 +00:00
'duration': 100.89,
'thumbnail': r're:^https?://.*\.jpg$',
2014-10-24 22:10:11 +00:00
'view_count': int,
2015-01-28 17:21:17 +00:00
'comment_count': int,
2014-10-24 22:10:11 +00:00
'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'],
}
}, {
2015-01-28 16:49:42 +00:00
'url': 'http://www.viddler.com/v/4d03aad9/',
2016-02-09 19:12:47 +00:00
'md5': 'f12c5a7fa839c47a79363bfdf69404fb',
2015-01-28 16:49:42 +00:00
'info_dict': {
'id': '4d03aad9',
2016-02-09 19:12:47 +00:00
'ext': 'ts',
2015-01-28 16:49:42 +00:00
'title': 'WALL-TO-GORTAT',
'upload_date': '20150126',
'uploader': 'deadspin',
'timestamp': 1422285291,
2015-01-28 17:21:17 +00:00
'view_count': int,
'comment_count': int,
}
}, {
2015-01-28 16:49:42 +00:00
'url': 'http://www.viddler.com/player/221ebbbd/0/',
2016-02-09 19:12:47 +00:00
'md5': '740511f61d3d1bb71dc14a0fe01a1c10',
2015-01-28 16:49:42 +00:00
'info_dict': {
'id': '221ebbbd',
2016-02-09 19:12:47 +00:00
'ext': 'mov',
2015-01-28 16:49:42 +00:00
'title': 'LETeens-Grammar-snack-third-conditional',
'description': ' ',
'upload_date': '20140929',
'uploader': 'BCLETeens',
'timestamp': 1411997190,
2015-01-28 17:21:17 +00:00
'view_count': int,
'comment_count': int,
}
}, {
# secret protected
'url': 'http://www.viddler.com/v/890c0985?secret=34051570',
'info_dict': {
'id': '890c0985',
'ext': 'mp4',
'title': 'Complete Property Training - Traineeships',
'description': ' ',
'upload_date': '20130606',
'uploader': 'TiffanyBowtell',
'timestamp': 1370496993,
'view_count': int,
'comment_count': int,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
2019-03-11 14:53:44 +00:00
video_id, secret = re.match(self._VALID_URL, url).groups()
2014-10-24 22:10:11 +00:00
query = {
'video_id': video_id,
'key': 'v0vhrt7bg2xq1vyxhkct',
}
if secret:
query['secret'] = secret
2019-03-11 14:53:44 +00:00
data = self._download_json(
'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json',
video_id, headers={'Referer': url}, query=query)['video']
2014-10-24 22:10:11 +00:00
formats = []
for filed in data['files']:
if filed.get('status', 'ready') != 'ready':
continue
2015-01-28 17:21:17 +00:00
format_id = filed.get('profile_id') or filed['profile_name']
2014-10-24 22:10:11 +00:00
f = {
2015-01-28 17:21:17 +00:00
'format_id': format_id,
2014-10-24 22:10:11 +00:00
'format_note': filed['profile_name'],
'url': self._proto_relative_url(filed['url']),
'width': int_or_none(filed.get('width')),
'height': int_or_none(filed.get('height')),
'filesize': int_or_none(filed.get('size')),
'ext': filed.get('ext'),
'source_preference': -1,
}
formats.append(f)
if filed.get('cdn_url'):
f = f.copy()
f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
2015-01-28 17:21:17 +00:00
f['format_id'] = format_id + '-cdn'
2014-10-24 22:10:11 +00:00
f['source_preference'] = 1
formats.append(f)
if filed.get('html5_video_source'):
f = f.copy()
2015-01-28 16:49:42 +00:00
f['url'] = self._proto_relative_url(filed['html5_video_source'])
2015-01-28 17:21:17 +00:00
f['format_id'] = format_id + '-html5'
2014-10-24 22:10:11 +00:00
f['source_preference'] = 0
formats.append(f)
self._sort_formats(formats)
categories = [
t.get('text') for t in data.get('tags', []) if 'text' in t]
return {
'id': video_id,
2014-10-24 22:10:11 +00:00
'title': data['title'],
'formats': formats,
2014-10-24 22:10:11 +00:00
'description': data.get('description'),
'timestamp': int_or_none(data.get('upload_time')),
'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
'uploader': data.get('author'),
'duration': float_or_none(data.get('length')),
'view_count': int_or_none(data.get('view_count')),
2015-01-28 17:21:17 +00:00
'comment_count': int_or_none(data.get('comment_count')),
2014-10-24 22:10:11 +00:00
'categories': categories,
}