X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvine.py;h=c733a48fa26edce6b219d3bf2404267b8c346bf6;hb=e4df2f98ccbe2e24785dd6883d7fd495193fd8e6;hp=689b8dc2a32cdf44b68ce001227b4316858ebc0d;hpb=acd69589a54d03f60a018a298c74a4c8aef2abc2;p=youtube-dl diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py index 689b8dc2a..c733a48fa 100644 --- a/youtube_dl/extractor/vine.py +++ b/youtube_dl/extractor/vine.py @@ -1,53 +1,81 @@ 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 = { + _VALID_URL = r'https?://(?:www\.)?vine\.co/(?:v|oembed)/(?P\w+)' + _TESTS = [{ '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', }, - } + }, { + 'url': 'https://vine.co/v/MYxVapFvz2z', + 'md5': '7b9a7cbc76734424ff942eb52c8f1065', + 'info_dict': { + 'id': 'MYxVapFvz2z', + 'ext': 'mp4', + 'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14', + 'alt_title': 'Vine by Luna', + 'description': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14', + 'upload_date': '20140815', + 'uploader': 'Luna', + 'uploader_id': '1102363502380728320', + }, + }, { + 'url': 'https://vine.co/v/bxVjBbZlPUH', + 'md5': 'ea27decea3fa670625aac92771a96b73', + 'info_dict': { + 'id': 'bxVjBbZlPUH', + 'ext': 'mp4', + 'title': '#mw3 #ac130 #killcam #angelofdeath', + 'alt_title': 'Vine by Z3k3', + 'description': '#mw3 #ac130 #killcam #angelofdeath', + 'upload_date': '20130430', + 'uploader': 'Z3k3', + 'uploader_id': '936470460173008896', + }, + }, { + 'url': 'https://vine.co/oembed/MYxVapFvz2z.json', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + 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')) - print(json.dumps(data, indent=2)) - formats = [ - { - 'url': data['videoLowURL'], - 'ext': 'mp4', - 'format_id': 'low', - }, - { - 'url': data['videoUrl'], - 'ext': 'mp4', - 'format_id': 'standard', - } - ] + data = self._parse_json( + self._html_search_regex( + r'window\.POST_DATA = { %s: ({.+?}) };\s*' % video_id, + webpage, 'vine data'), + video_id) + + 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, default=None), 'description': data['description'], 'thumbnail': data['thumbnailUrl'], 'upload_date': unified_strdate(data['created']), @@ -58,3 +86,47 @@ class VineIE(InfoExtractor): '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)