X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvine.py;h=46950d3a1499b20bec50a9482d47a0ebdbbfb8b3;hb=e8f20ffa032a791548a66bb7b694c424673537e6;hp=0b58fe0fe0b5188e9c9865e56ce064e94dbc45e5;hpb=ff21a8e0ee43d4ce0b75cd938f9bdfab664dd579;p=youtube-dl diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py index 0b58fe0fe..46950d3a1 100644 --- a/youtube_dl/extractor/vine.py +++ b/youtube_dl/extractor/vine.py @@ -1,59 +1,111 @@ +# 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 ( + determine_ext, + int_or_none, + unified_timestamp, +) 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.', + 'alt_title': 'Vine by Jack', + 'timestamp': 1368997951, 'upload_date': '20130519', - 'uploader': 'Jack Dorsey', + 'uploader': 'Jack', 'uploader_id': '76', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, - } + }, { + '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', + 'timestamp': 1436057405, + '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, + }, + }, { + 'url': 'https://vine.co/v/MYxVapFvz2z', + 'only_matching': True, + }, { + 'url': 'https://vine.co/v/bxVjBbZlPUH', + 'only_matching': True, + }, { + 'url': 'https://vine.co/oembed/MYxVapFvz2z.json', + 'only_matching': True, + }] 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: ({.+?}) }' % video_id, webpage, 'vine data')) + data = self._download_json( + 'https://archive.vine.co/posts/%s.json' % video_id, video_id) - formats = [{ - 'url': data['videoLowURL'], - 'ext': 'mp4', - 'format_id': 'low', - }, { - 'url': data['videoUrl'], - 'ext': 'mp4', - 'format_id': 'standard', - }] + def video_url(kind): + for url_suffix in ('Url', 'URL'): + format_url = data.get('video%s%s' % (kind, url_suffix)) + if format_url: + return format_url + + formats = [] + for quality, format_id in enumerate(('low', '', 'dash')): + format_url = video_url(format_id.capitalize()) + if not format_url: + continue + # DASH link returns plain mp4 + if format_id == 'dash' and determine_ext(format_url) == 'mpd': + formats.extend(self._extract_mpd_formats( + format_url, video_id, mpd_id='dash', fatal=False)) + else: + formats.append({ + 'url': format_url, + 'format_id': format_id or 'standard', + 'quality': quality, + }) + self._sort_formats(formats) + + username = data.get('username') + + alt_title = 'Vine by %s' % username if username else None 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'], + 'title': data.get('description') or alt_title or 'Vine video', + 'alt_title': alt_title, + 'thumbnail': data.get('thumbnailUrl'), + 'timestamp': unified_timestamp(data.get('created')), + 'uploader': username, + 'uploader_id': data.get('userIdStr'), + 'view_count': int_or_none(data.get('loops')), + 'like_count': int_or_none(data.get('likes')), + 'comment_count': int_or_none(data.get('comments')), + 'repost_count': int_or_none(data.get('reposts')), 'formats': formats, } @@ -61,7 +113,7 @@ class VineIE(InfoExtractor): class VineUserIE(InfoExtractor): IE_NAME = 'vine:user' _VALID_URL = r'(?:https?://)?vine\.co/(?Pu/)?(?P[^/]+)/?(\?.*)?$' - _VINE_BASE_URL = "https://vine.co/" + _VINE_BASE_URL = 'https://vine.co/' _TESTS = [ { 'url': 'https://vine.co/Visa', @@ -81,7 +133,7 @@ class VineUserIE(InfoExtractor): user = mobj.group('user') u = mobj.group('u') - profile_url = "%sapi/users/profiles/%s%s" % ( + 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') @@ -89,7 +141,7 @@ class VineUserIE(InfoExtractor): user_id = profile_data['data']['userId'] timeline_data = [] for pagenum in itertools.count(1): - timeline_url = "%sapi/timelines/users/%s?page=%s&size=100" % ( + 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)