from __future__ import unicode_literals import re import json import itertools from .common import InfoExtractor from ..utils import unified_strdate class VineIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?vine\.co/v/(?P\w+)' _TEST = { 'url': 'https://vine.co/v/b9KOOWX7HUx', 'md5': '2f36fed6235b16da96ce9b4dc890940d', 'info_dict': { 'id': 'b9KOOWX7HUx', 'ext': 'mp4', 'title': 'Chicken.', 'alt_title': 'Vine by Jack Dorsey', 'description': 'Chicken.', 'upload_date': '20130519', 'uploader': 'Jack Dorsey', 'uploader_id': '76', }, } def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id) data = json.loads(self._html_search_regex( r'window\.POST_DATA = { %s: ({.+?}) };\s*' % video_id, webpage, 'vine data')) formats = [{ 'format_id': '%(format)s-%(rate)s' % f, 'vcodec': f['format'], 'quality': f['rate'], 'url': f['videoUrl'], } for f in data['videoUrls']] self._sort_formats(formats) return { 'id': video_id, 'title': self._og_search_title(webpage), 'alt_title': self._og_search_description(webpage), 'description': data['description'], 'thumbnail': data['thumbnailUrl'], 'upload_date': unified_strdate(data['created']), 'uploader': data['username'], 'uploader_id': data['userIdStr'], 'like_count': data['likes']['count'], 'comment_count': data['comments']['count'], 'repost_count': data['reposts']['count'], 'formats': formats, } class VineUserIE(InfoExtractor): IE_NAME = 'vine:user' _VALID_URL = r'(?:https?://)?vine\.co/(?Pu/)?(?P[^/]+)/?(\?.*)?$' _VINE_BASE_URL = "https://vine.co/" _TESTS = [ { 'url': 'https://vine.co/Visa', 'info_dict': { 'id': 'Visa', }, 'playlist_mincount': 46, }, { 'url': 'https://vine.co/u/941705360593584128', 'only_matching': True, }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) user = mobj.group('user') u = mobj.group('u') profile_url = "%sapi/users/profiles/%s%s" % ( self._VINE_BASE_URL, 'vanity/' if not u else '', user) profile_data = self._download_json( profile_url, user, note='Downloading user profile data') user_id = profile_data['data']['userId'] timeline_data = [] for pagenum in itertools.count(1): timeline_url = "%sapi/timelines/users/%s?page=%s&size=100" % ( self._VINE_BASE_URL, user_id, pagenum) timeline_page = self._download_json( timeline_url, user, note='Downloading page %d' % pagenum) timeline_data.extend(timeline_page['data']['records']) if timeline_page['data']['nextPage'] is None: break entries = [ self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data] return self.playlist_result(entries, user)