当前位置：首页 > news >正文

Python数据爬取

news 来源：原创 2025/5/25 10:07:30

一.example1包下的

注意：需要在终端安装pip3 install -i https://requests.readthedocs.io/en/latest/ requests

1.Python网络爬虫初探-get请求

import requests
r=requests.get('https://www.baidu.com')
print(r.text)
r1=requests.get('https://www.jd.com')
print(r1.text)
r2=requests.get('https://httpbin.org/ip')
print(r2.text)

2.带参数的请求

import requests
data={"key1":"value1","key2":"value2"}
response=requests.get("http://httpbin.org/get",params=data)
print(response.text)
print(response.status_code)
print(response.headers)
print(response.url)

3.post请求

import requests
data={"name":"测试"}
response=requests.post("http://httpbin.org/post",data=data)
print(response.text)

4.获取响应数据

import requests
#获得图片
# response=requests.get('https://c-ssl.dtstatic.com/uploads/item/202004/17/20200417160907_laicg.thumb.400_0.gif')
# with open('baidu.png','wb') as f:
#     f.write(response.content)
#获得json格式的数据
response=requests.get('http://httpbin.org/ip')
data=response.json()
print(data)
print(data['origin'])
print(response.status_code)

5.自定义请求头信息

import requests
header={
    'user-agent':'baidu/v1'

}
response=requests.get('http://www.httpbin.org/get',headers=header)
print(response.request.headers)
print(response.headers)

6.设置超时时间

import requests

response=requests.get('http://github.com',timeout=1)#参数2为超时时长，单位是秒，通常情况设置2-3秒即可
print(response.text)

7.查询服务端的设置

#什么是cookie
#所谓的cookie就是服务端存放浏览器中的一些数据，这些数据可以包含访问的历史，历史记录，也可以是唯一标识等，
#获取cookie
import requests
#1.获取cookie
url="http://www.baidu.com"
header={
    'user-agent':'Mozilla/5.0 (X11; Linux aarch64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36 CrKey/1.54.250320 Edg/135.0.0.0'
}
response=requests.get(url,headers=header)
print(response.headers)
print(response.cookies)
print(response.cookies['BAIDUID'])

#2.设置cookie
url='http://www.httpbin.org/cookies'
cookies=dict(cookies_are='hello python')
response=requests.get(url,cookies=cookies)
print(response.text)

8.设置代理

import requests
url='http://whois.pconline.com.cn/ipJson.jsp?json=true'
response=requests.get(url)
print(response.text)
#使用代理
proxy={
    "http":"http://username:abcd1234@haha.xingsuaili.com:10010",
    "https":"http://username:abcd1234@haha.xingsuaili.com:10010"
}
response=requests.get(url,proxies=proxy)

9.证书设置

import requests

response=requests.get("https://www.hengxun.com/news/content/1028.html",verify=False)#参数2：verify=False，关闭证书校验，如果有证书，参数2指向证书位置，如verify='/path/to/certfile'

10.综合案例

import requests

header={
    'user-agent':'Mozilla/5.0 (X11; Linux aarch64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36 CrKey/1.54.250320 Edg/135.0.0.0'
}
for i in range(65151,65255):
    url="https://www.phei.com.cn/module/goods/wssd_content .jsp?bookid={}".format(i)
    response=requests.get(url,headers=header)
    html_file_name="page_{}.html".format(i)
    with open(html_file_name,"w",encoding='utf-8') as f:
        f.write(response.text)