[instagram:user] Add pagination (closes #15934)

This commit is contained in:
Sergey M․ 2018-03-21 23:43:03 +07:00
parent 3395958d2b
commit cba5d1b6b3
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -1,5 +1,6 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import itertools
import json import json
import re import re
@ -242,18 +243,27 @@ class InstagramUserIE(InfoExtractor):
return int_or_none(try_get( return int_or_none(try_get(
node, lambda x: x['edge_media_' + suffix]['count'])) node, lambda x: x['edge_media_' + suffix]['count']))
edges = self._download_json( cursor = ''
'https://www.instagram.com/graphql/query/', uploader_id, query={ for page_num in itertools.count(1):
media = self._download_json(
'https://www.instagram.com/graphql/query/', uploader_id,
'Downloading JSON page %d' % page_num, query={
'query_hash': '472f257a40c653c64c666ce877d59d2b', 'query_hash': '472f257a40c653c64c666ce877d59d2b',
'variables': json.dumps({ 'variables': json.dumps({
'id': uploader_id, 'id': uploader_id,
'first': 999999999, 'first': 100,
'after': cursor,
}) })
})['data']['user']['edge_owner_to_timeline_media']['edges'] })['data']['user']['edge_owner_to_timeline_media']
edges = media.get('edges')
if not edges or not isinstance(edges, list):
break
for edge in edges: for edge in edges:
node = edge['node'] node = edge.get('node')
if not node or not isinstance(node, dict):
continue
if node.get('__typename') != 'GraphVideo' and node.get('is_video') is not True: if node.get('__typename') != 'GraphVideo' and node.get('is_video') is not True:
continue continue
video_id = node.get('shortcode') video_id = node.get('shortcode')
@ -285,6 +295,18 @@ class InstagramUserIE(InfoExtractor):
yield info yield info
page_info = media.get('page_info')
if not page_info or not isinstance(page_info, dict):
break
has_next_page = page_info.get('has_next_page')
if not has_next_page:
break
cursor = page_info.get('end_cursor')
if not cursor or not isinstance(cursor, compat_str):
break
def _real_extract(self, url): def _real_extract(self, url):
username = self._match_id(url) username = self._match_id(url)
uploader_id = self._download_json( uploader_id = self._download_json(