PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-01-23 05:25:02 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[twitter] fix extraction (x.com)

Browse Source
This commit is contained in:
Mort Yao 2024-05-17 20:57:37 +02:00
parent a4d34ff6b1
commit 57f6502e80
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
3 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -376,7 +376,7 @@ Use `--url`/`-u` to get a list of downloadable resource URLs extracted from the
| Site | URL | Videos? | Images? | Audios? |
| :--: | :-- | :-----: | :-----: | :-----: |
| **YouTube** | <https://www.youtube.com/> |✓| | |
| **Twitter** | <https://twitter.com/> |✓|✓| |
| **X (Twitter)** | <https://x.com/> |✓|✓| |
| VK | <http://vk.com/> |✓|✓| |
| Vine | <https://vine.co/> |✓| | |
| Vimeo | <https://vimeo.com/> |✓| | |

8
src/you_get/common.py
View File

@ -113,6 +113,7 @@ SITES = {
'veoh' : 'veoh',
'vine' : 'vine',
'vk' : 'vk',
'x' : 'twitter',
'xiaokaxiu' : 'yixia',
'xiaojiadianvideo' : 'fc2video',
'ximalaya' : 'ximalaya',
@ -1856,9 +1857,12 @@ def url_to_module(url):
)
else:
try:
location = get_location(url) # t.co isn't happy with fake_headers
try:
location = get_location(url) # t.co isn't happy with fake_headers
except:
location = get_location(url, headers=fake_headers)
except:
location = get_location(url, headers=fake_headers)
location = get_location(url, headers=fake_headers, get_method='GET')
if location and location != url and not location.startswith('/'):
return url_to_module(location)

6
src/you_get/extractors/twitter.py
View File

@ -34,9 +34,9 @@ def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs)
**kwargs)
return
m = re.match('^https?://(mobile\.)?twitter\.com/([^/]+)/status/(\d+)', url)
m = re.match('^https?://(mobile\.)?(x|twitter)\.com/([^/]+)/status/(\d+)', url)
assert m
screen_name, item_id = m.group(2), m.group(3)
screen_name, item_id = m.group(3), m.group(4)
page_title = "{} [{}]".format(screen_name, item_id)
# FIXME: this API won't work for protected or nsfw contents
@ -77,6 +77,6 @@ def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs)
# TODO: should we deal with quoted tweets?
site_info = "Twitter.com"
site_info = "X.com"
download = twitter_download
download_playlist = playlist_not_supported('twitter')