PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-01-24 05:55:02 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[twitter] match correct screen_name and item_id in a conversation

Browse Source
This commit is contained in:
Mort Yao 2018-08-27 14:49:37 +02:00
parent e36404cf22
commit 2a1bb6978c
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/you_get/extractors/twitter.py
View File

@ -30,9 +30,9 @@ def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs)
return return
html = get_html(url, faker=True) html = get_html(url, faker=True)
screen_name = r1(r'data-screen-name="([^"]*)"', html) or \ screen_name = r1(r'twitter\.com/([^/]+)', url) or r1(r'data-screen-name="([^"]*)"', html) or \
r1(r'<meta name="twitter:title" content="([^"]*)"', html) r1(r'<meta name="twitter:title" content="([^"]*)"', html)
item_id = r1(r'data-item-id="([^"]*)"', html) or \ item_id = r1(r'twitter\.com/[^/]+/status/(\d+)', url) or r1(r'data-item-id="([^"]*)"', html) or \
r1(r'<meta name="twitter:site:id" content="([^"]*)"', html) r1(r'<meta name="twitter:site:id" content="([^"]*)"', html)
page_title = "{} [{}]".format(screen_name, item_id) page_title = "{} [{}]".format(screen_name, item_id)