Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-02 17:22:31 +01:00
Code Issues Releases Activity

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

Browse Source
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
1 changed files with 59 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

96
youtube_dl/extractor/instagram.py
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
@ -242,48 +243,69 @@ def get_count(suffix):
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):
'query_hash': '472f257a40c653c64c666ce877d59d2b', media = self._download_json(
'variables': json.dumps({ 'https://www.instagram.com/graphql/query/', uploader_id,
'id': uploader_id, 'Downloading JSON page %d' % page_num, query={
'first': 999999999, 'query_hash': '472f257a40c653c64c666ce877d59d2b',
'variables': json.dumps({
'id': uploader_id,
'first': 100,
'after': cursor,
})
})['data']['user']['edge_owner_to_timeline_media']
edges = media.get('edges')
if not edges or not isinstance(edges, list):
break
for edge in edges:
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:
continue
video_id = node.get('shortcode')
if not video_id:
continue
info = self.url_result(
'https://instagram.com/p/%s/' % video_id,
ie=InstagramIE.ie_key(), video_id=video_id)
description = try_get(
node, lambda x: x['edge_media_to_caption']['edges'][0]['node']['text'],
compat_str)
thumbnail = node.get('thumbnail_src') or node.get('display_src')
timestamp = int_or_none(node.get('taken_at_timestamp'))
comment_count = get_count('to_comment')
like_count = get_count('preview_like')
view_count = int_or_none(node.get('video_view_count'))
info.update({
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'comment_count': comment_count,
'like_count': like_count,
'view_count': view_count,
}) })
})['data']['user']['edge_owner_to_timeline_media']['edges']
for edge in edges: yield info
node = edge['node']
if node.get('__typename') != 'GraphVideo' and node.get('is_video') is not True: page_info = media.get('page_info')
continue if not page_info or not isinstance(page_info, dict):
video_id = node.get('shortcode') break
if not video_id:
continue
info = self.url_result( has_next_page = page_info.get('has_next_page')
'https://instagram.com/p/%s/' % video_id, if not has_next_page:
ie=InstagramIE.ie_key(), video_id=video_id) break
description = try_get( cursor = page_info.get('end_cursor')
node, lambda x: x['edge_media_to_caption']['edges'][0]['node']['text'], if not cursor or not isinstance(cursor, compat_str):
compat_str) break
thumbnail = node.get('thumbnail_src') or node.get('display_src')
timestamp = int_or_none(node.get('taken_at_timestamp'))
comment_count = get_count('to_comment')
like_count = get_count('preview_like')
view_count = int_or_none(node.get('video_view_count'))
info.update({
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'comment_count': comment_count,
'like_count': like_count,
'view_count': view_count,
})
yield info
def _real_extract(self, url): def _real_extract(self, url):
username = self._match_id(url) username = self._match_id(url)