yt-dlp/youtube_dl/extractor/vine.py

101 lines
3.2 KiB
Python
Raw Normal View History

2014-01-31 13:17:21 +00:00
from __future__ import unicode_literals
2013-06-23 20:26:30 +00:00
import re
import json
import itertools
2013-06-23 20:26:30 +00:00
from .common import InfoExtractor
from ..utils import unified_strdate
2013-06-23 20:26:30 +00:00
class VineIE(InfoExtractor):
2014-01-31 13:17:21 +00:00
_VALID_URL = r'https?://(?:www\.)?vine\.co/v/(?P<id>\w+)'
2013-06-27 18:46:46 +00:00
_TEST = {
2014-01-31 13:17:21 +00:00
'url': 'https://vine.co/v/b9KOOWX7HUx',
'md5': '2f36fed6235b16da96ce9b4dc890940d',
'info_dict': {
'id': 'b9KOOWX7HUx',
'ext': 'mp4',
'title': 'Chicken.',
'description': 'Chicken.',
'upload_date': '20130519',
'uploader': 'Jack Dorsey',
'uploader_id': '76',
2014-01-31 13:17:21 +00:00
},
2013-06-27 18:46:46 +00:00
}
2013-06-23 20:26:30 +00:00
def _real_extract(self, url):
2014-12-12 01:59:52 +00:00
video_id = self._match_id(url)
webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
2013-06-23 20:26:30 +00:00
data = json.loads(self._html_search_regex(
r'window\.POST_DATA = { %s: ({.+?}) }' % video_id, webpage, 'vine data'))
2014-04-30 12:12:30 +00:00
2014-12-12 01:59:52 +00:00
formats = [{
'url': data['videoLowURL'],
'ext': 'mp4',
'format_id': 'low',
}, {
'url': data['videoUrl'],
'ext': 'mp4',
'format_id': 'standard',
}]
2013-06-23 20:26:30 +00:00
2014-01-31 13:17:21 +00:00
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'],
'formats': formats,
}
2014-05-13 07:50:03 +00:00
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 07:50:03 +00:00
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 07:50:03 +00:00
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 07:50:03 +00:00
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 07:50:03 +00:00
entries = [
self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data]
return self.playlist_result(entries, user)