批量获取网站百度谷歌360权重Python源码，采用随机ua，批量抓取网站的权重。
import requests
from bs4 import BeautifulSoup
import time
import random
# 读取文件内容
with open('www.txt', 'r') as f:
content = f.read()
# 提取域名列表
domains = content.split('\n')
# 定义多个User-Agent头部
user_agents = [
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Safari/537.36',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101 Firefox/78.0',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36',
# 更多 User-Agent 头部...
]
# 遍历域名列表
for domain in domains:
# 随机选取一个 User-Agent 头部
user_agent = random.choice(user_agents)
headers = {'User-Agent': user_agent}
# 发送请求
url = f'https://www.aizhan.com/cha/{domain}/'
res = requests.get(url, headers=headers)
# 解析响应
soup = BeautifulSoup(res.text, 'html.parser')
baidu_rank_img = soup.find(id='baidurank_br').find('img')
baidu_rank = baidu_rank_img['alt']
if baidu_rank != "n":
baidu_rank = int(baidu_rank)
else:
baidu_rank = int("0")
# 找到移动权重信息
mobile_rank_img = soup.find(id='baidurank_mbr').find('img')
mobile_rank = mobile_rank_img['alt']
if mobile_rank != "n":
mobile_rank = int(mobile_rank)
else:
mobile_rank = int("0")
# 找到360权重信息
so_rank_img = soup.find(id='360_pr').find('img')
so_rank_rank = so_rank_img['alt']
if so_rank_rank != "n":
so_rank_rank = int(so_rank_rank)
else:
so_rank_rank = int("0")
# 找到谷歌权重信息
google_rank_img = soup.find(id='google_pr').find('img')
if google_rank_img:
google_rank = int(google_rank_img['alt'])
if baidu_rank >= 1 or mobile_rank >= 1 or google_rank >= 3:
print(f"{domain}")
# 暂停 1 到 2 秒之间的随机时间
time.sleep(random.randint(1, 2))