requests用法

1
import requests #请求
2
from threading import Thread#多线程
3
from lxml import etree#xpath
4
import re#正则
5
from bs4 import BeautifulSoup #bs4
6

7
#UA
8
UA = {"User-Agent":
9
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36"}
10

11

12
# 设置 SOCKS 代理
13
proxy_address = '127.0.0.1'  # 代理地址
14
proxy_port = '1080'  # 代理端口号
15

16
# 构建 SOCKS 代理地址
17
proxy_url = f'socks5://{proxy_address}:{proxy_port}'
18

19
# 设置 HTTP 代理
20
proxy_username = 'P55fRHQTMd'  # 代理用户名
21
proxy_password = 'CmFA0OVr8X'  # 代理密码
22
proxy_address = '23.106.140.216'  # 代理地址
23
proxy_port = '21443'  # 代理端口号
24

25

26
# 构建 HTTP 代理地址
27
proxy_url = f'http://{proxy_username}:{proxy_password}@{proxy_address}:{proxy_port}'
28

29
#GET
30
get = requests.get(domain, headers=UA , proxies={'http': proxy_url, 'https': proxy_url})
31

32

33
#bs4
34
page = BeautifulSoup(get.text, "html.parser")
35
名称 = page.find("标签", class_="内容")
36
#正则表达式
37
obj = re.compile(r'正则表所式',re.S)
38
名称 = obj.findall(get.text)
39
#xpath
40
html = etree.HTML(get.text)
41
名称 = html.xpath("路径/text()")