jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-04-20 18:57:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: 微博支持评论 & 指定帖子

Browse Source
This commit is contained in:
Relakkes
2023-12-25 00:02:11 +08:00
parent b1441ab4ae
commit eee81622ac
12 changed files with 228 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
tools/crawler_util.py
View File

@@ -54,6 +54,20 @@ def get_user_agent() -> str:
return random.choice(ua_list)
def get_mobile_user_agent() -> str:
ua_list = [
"Mozilla/5.0 (iPhone; CPU iPhone OS 16_5 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.5 Mobile/15E148 Safari/604.1",
"Mozilla/5.0 (iPad; CPU OS 16_5 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.5 Mobile/15E148 Safari/604.1",
"Mozilla/5.0 (iPhone; CPU iPhone OS 16_5 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) CriOS/114.0.5735.99 Mobile/15E148 Safari/604.1",
"Mozilla/5.0 (iPad; CPU OS 16_5 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) CriOS/114.0.5735.124 Mobile/15E148 Safari/604.1",
"Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Mobile Safari/537.36",
"Mozilla/5.0 (Linux; Android 13; SAMSUNG SM-S918B) AppleWebKit/537.36 (KHTML, like Gecko) SamsungBrowser/21.0 Chrome/110.0.5481.154 Mobile Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36 OPR/99.0.0.0",
"Mozilla/5.0 (Linux; Android 10; JNY-LX1; HMSCore 6.11.0.302) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.88 HuaweiBrowser/13.0.5.303 Mobile Safari/537.36"
]
return random.choice(ua_list)
def convert_cookies(cookies: Optional[List[Cookie]]) -> Tuple[str, Dict]:
if not cookies:
return "", {}

2
tools/time_util.py
View File

@@ -4,7 +4,7 @@
# @Desc : 时间相关的工具函数
import time
from datetime import datetime, timezone, timedelta
from datetime import datetime, timedelta, timezone
def get_current_timestamp() -> int: