X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9815bb0a551468e4939cacfffbc2d5cb8dd12431..10a637f94cdc8521231ed6b1b56a9ff2f5601330:/youtube_dl/extractor/vine.py diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py index b44b1cb..0b58fe0 100644 --- a/youtube_dl/extractor/vine.py +++ b/youtube_dl/extractor/vine.py @@ -1,37 +1,102 @@ +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+)' + _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): - mobj = re.match(self._VALID_URL, 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: ({.+?}) }' % video_id, webpage, 'vine data')) + + formats = [{ + 'url': data['videoLowURL'], + 'ext': 'mp4', + 'format_id': 'low', + }, { + 'url': data['videoUrl'], + 'ext': 'mp4', + 'format_id': 'standard', + }] - video_id = mobj.group('id') - webpage_url = 'https://vine.co/v/' + video_id - webpage = self._download_webpage(webpage_url, video_id) + 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, + } - self.report_extraction(video_id) - video_url = self._html_search_regex(r'u/)?(?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, + }, + ] - video_title = self._html_search_regex(r'.*?

(.+?)

', - webpage, u'uploader', fatal=False, flags=re.DOTALL) + 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 - return [{ - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': video_title, - 'thumbnail': thumbnail, - 'uploader': uploader, - }] + entries = [ + self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data] + return self.playlist_result(entries, user)