X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/90cd207d52d77e075e62cc256cc39dceee05bbf3..aebf9c8f14c9f5d45f8c6aa523ee135fdfd421b2:/youtube_dl/extractor/viddler.py diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py index 826804a..6bfbd4d 100644 --- a/youtube_dl/extractor/viddler.py +++ b/youtube_dl/extractor/viddler.py @@ -1,64 +1,146 @@ -import json -import re +from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urlparse, +) from ..utils import ( - determine_ext, + float_or_none, + int_or_none, + sanitized_Request, ) class ViddlerIE(InfoExtractor): - _VALID_URL = r'(?Phttps?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P[a-z0-9]+)' - _TEST = { - u"url": u"http://www.viddler.com/v/43903784", - u'file': u'43903784.mp4', - u'md5': u'fbbaedf7813e514eb7ca30410f439ac9', - u'info_dict': { - u"title": u"Video Made Easy", - u"uploader": u"viddler", - u"duration": 100.89, + _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P[a-z0-9]+)' + _TESTS = [{ + 'url': 'http://www.viddler.com/v/43903784', + 'md5': '9eee21161d2c7f5b39690c3e325fab2f', + 'info_dict': { + 'id': '43903784', + 'ext': 'mov', + 'title': 'Video Made Easy', + 'description': 'md5:6a697ebd844ff3093bd2e82c37b409cd', + 'uploader': 'viddler', + 'timestamp': 1335371429, + 'upload_date': '20120425', + 'duration': 100.89, + 'thumbnail': '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): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + + query = { + 'video_id': video_id, + 'key': 'v0vhrt7bg2xq1vyxhkct', + } - embed_url = mobj.group('domain') + u'/embed/' + video_id - webpage = self._download_webpage(embed_url, video_id) + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + secret = qs.get('secret', [None])[0] + if secret: + query['secret'] = secret - video_sources_code = self._search_regex( - r"(?ms)sources\s*:\s*(\{.*?\})", webpage, u'video URLs') - video_sources = json.loads(video_sources_code.replace("'", '"')) + headers = {'Referer': 'http://static.cdn-ec.viddler.com/js/arpeggio/v2/embed.html'} + request = sanitized_Request( + 'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?%s' + % compat_urllib_parse.urlencode(query), None, headers) + data = self._download_json(request, video_id)['video'] - formats = [{ - 'url': video_url, - 'format': format_id, - } for video_url, format_id in video_sources.items()] + 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': format_id, + '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) - title = self._html_search_regex( - r"title\s*:\s*'([^']*)'", webpage, u'title') - uploader = self._html_search_regex( - r"authorName\s*:\s*'([^']*)'", webpage, u'uploader', fatal=False) - duration_s = self._html_search_regex( - r"duration\s*:\s*([0-9.]*)", webpage, u'duration', fatal=False) - duration = float(duration_s) if duration_s else None - thumbnail = self._html_search_regex( - r"thumbnail\s*:\s*'([^']*)'", - webpage, u'thumbnail', fatal=False) + if filed.get('cdn_url'): + f = f.copy() + f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:') + f['format_id'] = format_id + '-cdn' + f['source_preference'] = 1 + formats.append(f) - info = { - '_type': 'video', + if filed.get('html5_video_source'): + f = f.copy() + 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) + + categories = [ + t.get('text') for t in data.get('tags', []) if 'text' in t] + + return { 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'duration': duration, + 'title': data['title'], 'formats': formats, + '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')), + 'comment_count': int_or_none(data.get('comment_count')), + 'categories': categories, } - - # TODO: Remove when #980 has been merged - info['formats'][-1]['ext'] = determine_ext(info['formats'][-1]['url']) - info.update(info['formats'][-1]) - - return info