1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-05 05:12:56 +01:00
youtube-dl/youtube_dl/extractor/vine.py

161 lines
5.5 KiB
Python
Raw Normal View History

# coding: utf-8
2014-01-31 14:17:21 +01:00
from __future__ import unicode_literals
2013-06-23 22:26:30 +02:00
import re
import itertools
2013-06-23 22:26:30 +02:00
from .common import InfoExtractor
from ..utils import (
int_or_none,
unified_strdate,
)
2013-06-23 22:26:30 +02:00
class VineIE(InfoExtractor):
2015-04-09 18:40:18 +02:00
_VALID_URL = r'https?://(?:www\.)?vine\.co/(?:v|oembed)/(?P<id>\w+)'
2015-04-09 18:37:54 +02:00
_TESTS = [{
2014-01-31 14:17:21 +01:00
'url': 'https://vine.co/v/b9KOOWX7HUx',
'md5': '2f36fed6235b16da96ce9b4dc890940d',
'info_dict': {
'id': 'b9KOOWX7HUx',
'ext': 'mp4',
'title': 'Chicken.',
2014-12-12 03:34:28 +01:00
'alt_title': 'Vine by Jack Dorsey',
'upload_date': '20130519',
'uploader': 'Jack Dorsey',
'uploader_id': '76',
2015-10-18 05:36:19 +02:00
'like_count': int,
'comment_count': int,
'repost_count': int,
2014-01-31 14:17:21 +01:00
},
2015-04-09 18:37:54 +02:00
}, {
'url': 'https://vine.co/v/MYxVapFvz2z',
'md5': '7b9a7cbc76734424ff942eb52c8f1065',
'info_dict': {
'id': 'MYxVapFvz2z',
'ext': 'mp4',
'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
2015-10-17 22:29:49 +02:00
'alt_title': 'Vine by Mars Ruiz',
2015-04-09 18:37:54 +02:00
'upload_date': '20140815',
2015-10-17 22:29:49 +02:00
'uploader': 'Mars Ruiz',
2015-04-09 18:37:54 +02:00
'uploader_id': '1102363502380728320',
2015-10-18 05:36:19 +02:00
'like_count': int,
'comment_count': int,
'repost_count': int,
2015-04-09 18:37:54 +02:00
},
}, {
'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',
2015-10-18 05:36:19 +02:00
'like_count': int,
'comment_count': int,
'repost_count': int,
2015-04-09 18:37:54 +02:00
},
2015-04-09 18:40:18 +02:00
}, {
'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',
2015-10-18 05:36:19 +02:00
'like_count': int,
'comment_count': int,
'repost_count': int,
},
'params': {
'skip_download': True,
},
2015-04-09 18:37:54 +02:00
}]
2013-06-23 22:26:30 +02:00
def _real_extract(self, url):
2014-12-12 02:59:52 +01:00
video_id = self._match_id(url)
webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
2013-06-23 22:26:30 +02:00
2015-04-09 18:41:41 +02:00
data = self._parse_json(
self._search_regex(
r'window\.POST_DATA\s*=\s*{\s*%s\s*:\s*({.+?})\s*};\s*</script>' % video_id,
2015-04-09 18:41:41 +02:00
webpage, 'vine data'),
video_id)
2014-04-30 14:12:30 +02:00
2014-12-12 02:59:52 +01:00
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)
2013-06-23 22:26:30 +02:00
username = data.get('username')
2014-01-31 14:17:21 +01:00
return {
'id': video_id,
'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'),
'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,
}
2014-05-13 09:50:03 +02:00
class VineUserIE(InfoExtractor):
IE_NAME = 'vine:user'
_VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'
_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,
},
]
2014-05-13 09:50:03 +02:00
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)
2014-05-13 09:50:03 +02:00
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" % (
2014-05-13 09:50:03 +02:00
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
2014-05-13 09:50:03 +02:00
entries = [
self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data]
return self.playlist_result(entries, user)