X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/6d835d4d6903cf5e18ad01844736929e06d16004..9865587cf7b579793ba274067c3e44065d5ff77d:/youtube_dl/extractor/viddler.py?ds=sidebyside diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py index 0faa729..6423584 100644 --- a/youtube_dl/extractor/viddler.py +++ b/youtube_dl/extractor/viddler.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( float_or_none, @@ -8,39 +10,91 @@ from ..utils import ( class ViddlerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P[a-z0-9]+)' - _TEST = { - "url": "http://www.viddler.com/v/43903784", - 'md5': 'ae43ad7cb59431ce043f0ff7fa13cbf4', + _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P[a-z0-9]+)(?:.+?\bsecret=(\d+))?' + _TESTS = [{ + 'url': 'http://www.viddler.com/v/43903784', + 'md5': '9eee21161d2c7f5b39690c3e325fab2f', 'info_dict': { 'id': '43903784', - 'ext': 'mp4', - "title": "Video Made Easy", - 'description': 'You don\'t need to be a professional to make high-quality video content. Viddler provides some quick and easy tips on how to produce great video content with limited resources. ', - "uploader": "viddler", + 'ext': 'mov', + 'title': 'Video Made Easy', + 'description': 'md5:6a697ebd844ff3093bd2e82c37b409cd', + 'uploader': 'viddler', 'timestamp': 1335371429, 'upload_date': '20120425', - "duration": 100.89, - 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 100.89, + 'thumbnail': r're:^https?://.*\.jpg$', 'view_count': int, + 'comment_count': int, 'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'], } - } + }, { + 'url': 'http://www.viddler.com/v/4d03aad9/', + 'md5': 'f12c5a7fa839c47a79363bfdf69404fb', + 'info_dict': { + 'id': '4d03aad9', + 'ext': 'ts', + 'title': 'WALL-TO-GORTAT', + 'upload_date': '20150126', + 'uploader': 'deadspin', + 'timestamp': 1422285291, + 'view_count': int, + 'comment_count': int, + } + }, { + 'url': 'http://www.viddler.com/player/221ebbbd/0/', + 'md5': '740511f61d3d1bb71dc14a0fe01a1c10', + 'info_dict': { + 'id': '221ebbbd', + 'ext': 'mov', + 'title': 'LETeens-Grammar-snack-third-conditional', + 'description': ' ', + 'upload_date': '20140929', + 'uploader': 'BCLETeens', + 'timestamp': 1411997190, + '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): - video_id = self._match_id(url) + video_id, secret = re.match(self._VALID_URL, url).groups() + + query = { + 'video_id': video_id, + 'key': 'v0vhrt7bg2xq1vyxhkct', + } + if secret: + query['secret'] = secret - json_url = ( - 'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?video_id=%s&key=v0vhrt7bg2xq1vyxhkct' % - video_id) - data = self._download_json(json_url, video_id)['video'] + data = self._download_json( + 'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json', + video_id, headers={'Referer': url}, query=query)['video'] formats = [] for filed in data['files']: if filed.get('status', 'ready') != 'ready': continue + format_id = filed.get('profile_id') or filed['profile_name'] f = { - 'format_id': filed['profile_id'], + 'format_id': format_id, 'format_note': filed['profile_name'], 'url': self._proto_relative_url(filed['url']), 'width': int_or_none(filed.get('width')), @@ -53,16 +107,15 @@ class ViddlerIE(InfoExtractor): if filed.get('cdn_url'): f = f.copy() - f['url'] = self._proto_relative_url(filed['cdn_url']) - f['format_id'] = filed['profile_id'] + '-cdn' + f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:') + f['format_id'] = format_id + '-cdn' f['source_preference'] = 1 formats.append(f) if filed.get('html5_video_source'): f = f.copy() - f['url'] = self._proto_relative_url( - filed['html5_video_source']) - f['format_id'] = filed['profile_id'] + '-html5' + f['url'] = self._proto_relative_url(filed['html5_video_source']) + f['format_id'] = format_id + '-html5' f['source_preference'] = 0 formats.append(f) self._sort_formats(formats) @@ -71,7 +124,6 @@ class ViddlerIE(InfoExtractor): t.get('text') for t in data.get('tags', []) if 'text' in t] return { - '_type': 'video', 'id': video_id, 'title': data['title'], 'formats': formats, @@ -81,5 +133,6 @@ class ViddlerIE(InfoExtractor): 'uploader': data.get('author'), 'duration': float_or_none(data.get('length')), 'view_count': int_or_none(data.get('view_count')), + 'comment_count': int_or_none(data.get('comment_count')), 'categories': categories, }