vndangkhoa/kv-tiktok-download
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

🗳修复TikTok部分短链接解析失败的问题

Browse source
This commit is contained in:
Evil0ctal 2022-04-06 11:31:57 -07:00 committed by GitHub
parent 57d2554627
commit 44e4835849
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
Web/scraper.py
View file

@ -20,6 +20,7 @@ class Scraper:
Scraper.douyin():抖音视频/图集解析，返回字典。 Scraper.douyin():抖音视频/图集解析，返回字典。
Scraper.tiktok():TikTok视频解析，返回字典。 Scraper.tiktok():TikTok视频解析，返回字典。
""" """
def __init__(self): def __init__(self):
self.headers = { self.headers = {
'user-agent': 'Mozilla/5.0 (Linux; Android 8.0; Pixel 2 Build/OPD3.170816.012) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Mobile Safari/537.36 Edg/87.0.664.66' 'user-agent': 'Mozilla/5.0 (Linux; Android 8.0; Pixel 2 Build/OPD3.170816.012) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Mobile Safari/537.36 Edg/87.0.664.66'
@ -248,6 +249,7 @@ class Scraper:
# 从请求头中获取原始链接 # 从请求头中获取原始链接
response = requests.get(url=original_url, headers=headers, allow_redirects=False) response = requests.get(url=original_url, headers=headers, allow_redirects=False)
true_link = response.headers['Location'].split("?")[0] true_link = response.headers['Location'].split("?")[0]
original_url = true_link
# TikTok请求头返回的第二种链接类型 # TikTok请求头返回的第二种链接类型
if '.html' in true_link: if '.html' in true_link:
response = requests.get(url=true_link, headers=headers, allow_redirects=False) response = requests.get(url=true_link, headers=headers, allow_redirects=False)
@ -361,7 +363,7 @@ class Scraper:
'video_comment_count': video_comment_count, 'video_comment_count': video_comment_count,
'video_digg_count': video_digg_count, 'video_digg_count': video_digg_count,
'video_play_count': video_play_count, 'video_play_count': video_play_count,
'video_share_count':video_share_count, 'video_share_count': video_share_count,
'video_author_followerCount': video_author_followerCount, 'video_author_followerCount': video_author_followerCount,
'video_author_followingCount': video_author_followingCount, 'video_author_followingCount': video_author_followingCount,
'video_author_heartCount': video_author_heartCount, 'video_author_heartCount': video_author_heartCount,
@ -385,4 +387,4 @@ if __name__ == '__main__':
print('') print('')
douyin_url = "https://www.douyin.com/video/7036277592986537252" douyin_url = "https://www.douyin.com/video/7036277592986537252"
douyin_date = scraper.douyin(douyin_url) douyin_date = scraper.douyin(douyin_url)
print(douyin_date) print(douyin_date)