PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-11 20:52:31 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[bilibili] use faker when downloading videos

Browse Source 
Bilibili's CDN now may reject requests with 403 when urllib's default
user agent is used. This appears to be location-based (and started today
for me; others might have experienced this for a while): I tested on a
bunch of U.S.-based nodes and all requests were rejected without a
spoofed user agent, but when I tested on a Mainland China-based node,
the requests went through.
This commit is contained in:
Zhiming Wang 2017-05-25 15:37:54 -04:00
parent 23011a011c
commit 3c8c65f045
No known key found for this signature in database
GPG Key ID: 5B58F95EC95965D8
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/you_get/extractors/bilibili.py
View File

@ -77,12 +77,12 @@ def bilibili_download_by_cids(cids, title, output_dir='.', merge=True, info_only
type_ = '' type_ = ''
size = 0 size = 0
for url in urls: for url in urls:
_, type_, temp = url_info(url) _, type_, temp = url_info(url, faker=True, headers={'Referer': 'http://www.bilibili.com/'})
size += temp size += temp
print_info(site_info, title, type_, size) print_info(site_info, title, type_, size)
if not info_only: if not info_only:
download_urls(urls, title, type_, total_size=None, output_dir=output_dir, merge=merge, headers={'Referer': 'http://www.bilibili.com/'}) download_urls(urls, title, type_, total_size=None, output_dir=output_dir, merge=merge, faker=True, headers={'Referer': 'http://www.bilibili.com/'})
def bilibili_download_by_cid(cid, title, output_dir='.', merge=True, info_only=False): def bilibili_download_by_cid(cid, title, output_dir='.', merge=True, info_only=False):
@ -98,12 +98,12 @@ def bilibili_download_by_cid(cid, title, output_dir='.', merge=True, info_only=F
type_ = '' type_ = ''
size = 0 size = 0
for url in urls: for url in urls:
_, type_, temp = url_info(url, headers={'Referer': 'http://www.bilibili.com/'}) _, type_, temp = url_info(url, faker=True, headers={'Referer': 'http://www.bilibili.com/'})
size += temp or 0 size += temp or 0
print_info(site_info, title, type_, size) print_info(site_info, title, type_, size)
if not info_only: if not info_only:
download_urls(urls, title, type_, total_size=None, output_dir=output_dir, merge=merge, timeout=1, headers={'Referer': 'http://www.bilibili.com/'}) download_urls(urls, title, type_, total_size=None, output_dir=output_dir, merge=merge, timeout=1, faker=True, headers={'Referer': 'http://www.bilibili.com/'})
except socket.timeout: except socket.timeout:
continue continue
else: else: