X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/c512650955de0b16d37e7fa7fb29ea0985e415bb..bcccf25821fdedf4d89a8f8847cfb5660a10da94:/youtube_dl/extractor/vine.py diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py index 076c871..5b80184 100644 --- a/youtube_dl/extractor/vine.py +++ b/youtube_dl/extractor/vine.py @@ -1,84 +1,158 @@ +# coding: utf-8 from __future__ import unicode_literals import re -import json import itertools from .common import InfoExtractor -from ..utils import unified_strdate +from ..utils import ( + int_or_none, + 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.', - 'description': 'Chicken.', + 'alt_title': 'Vine by Jack Dorsey', 'upload_date': '20130519', 'uploader': 'Jack Dorsey', 'uploader_id': '76', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, - } + }, { + '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 Mars Ruiz', + 'upload_date': '20140815', + 'uploader': 'Mars Ruiz', + 'uploader_id': '1102363502380728320', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, + }, + }, { + 'url': 'https://vine.co/v/bxVjBbZlPUH', + 'md5': 'ea27decea3fa670625aac92771a96b73', + 'info_dict': { + 'id': 'bxVjBbZlPUH', + 'ext': 'mp4', + 'title': '#mw3 #ac130 #killcam #angelofdeath', + 'alt_title': 'Vine by Z3k3', + 'upload_date': '20130430', + 'uploader': 'Z3k3', + 'uploader_id': '936470460173008896', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, + }, + }, { + 'url': 'https://vine.co/oembed/MYxVapFvz2z.json', + 'only_matching': True, + }, { + 'url': 'https://vine.co/v/e192BnZnZ9V', + 'info_dict': { + 'id': 'e192BnZnZ9V', + 'ext': 'mp4', + 'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries #lovesickseason2', + 'alt_title': 'Vine by Pimry_zaa', + 'upload_date': '20150705', + 'uploader': 'Pimry_zaa', + 'uploader_id': '1135760698325307392', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_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) 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')) + data = self._parse_json( + self._search_regex( + r'window\.POST_DATA\s*=\s*{\s*%s\s*:\s*({.+?})\s*};\s*' % video_id, + webpage, 'vine data'), + video_id) - formats = [ - { - 'url': data['videoLowURL'], - 'ext': 'mp4', - 'format_id': 'low', - }, - { - 'url': data['videoUrl'], - 'ext': 'mp4', - 'format_id': 'standard', - } - ] + formats = [{ + 'format_id': '%(format)s-%(rate)s' % f, + 'vcodec': f.get('format'), + 'quality': f.get('rate'), + 'url': f['videoUrl'], + } for f in data['videoUrls'] if f.get('videoUrl')] + + self._sort_formats(formats) + + username = data.get('username') return { 'id': video_id, - 'title': self._og_search_title(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'], + 'title': data.get('description') or self._og_search_title(webpage), + 'alt_title': 'Vine by %s' % username if username else self._og_search_description(webpage, default=None), + 'thumbnail': data.get('thumbnailUrl'), + 'upload_date': unified_strdate(data.get('created')), + 'uploader': username, + 'uploader_id': data.get('userIdStr'), + 'view_count': int_or_none(data.get('loops', {}).get('count')), + 'like_count': int_or_none(data.get('likes', {}).get('count')), + 'comment_count': int_or_none(data.get('comments', {}).get('count')), + 'repost_count': int_or_none(data.get('reposts', {}).get('count')), 'formats': formats, } class VineUserIE(InfoExtractor): IE_NAME = 'vine:user' - _VALID_URL = r'(?:https?://)?vine\.co/(?P[^/]+)/?(\?.*)?$' - _VINE_BASE_URL = "https://vine.co/" + _VALID_URL = r'(?:https?://)?vine\.co/(?Pu/)?(?P[^/]+)/?(\?.*)?$' + _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/vanity/%s" % ( - self._VINE_BASE_URL, user) + 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" % ( + 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)