python开发:爬虫示例——GET和POST请求处理

一、Get请求

python 复制代码
import json
import requests

#输入示例:url='https://www.baidu.com'
#RequestHeader:F12标头-请求标头-原始-复制到这(忽略第一句)
def GetRequest(url,RequestHeader=""):
    try:
        dic={}
        RequestHeaderList = RequestHeader.strip().split("\n")
        if RequestHeader!="":
            for item in RequestHeaderList:
                if ":" in item:
                    key = item.split(":")[0].strip()
                    value = item.split(":")[1].strip()
                    dic[key] = value
        else:
            dic["User-Agent"]="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/132.0.0.0 Safari/537.36 Edg/132.0.0.0"
            #dic["Cookie"]=""
        response=requests.get(url=url,headers=dic)  ##跳过安全验证:逗号补充一个"verify=False"
        response.encoding='utf-8'  ##一般填写utf-8或者gbk
        data=response.json() #获取json字符串
        data = json.dumps(data, indent=4, sort_keys=True, ensure_ascii=False)#字符串格式化为json
        #print(data)#打印Json
        response.close()
        data = json.loads(data)#json转化为py字典
        #print(data)#打印字典
        return data
    except Exception as ex:
        print(f"爬取异常,错误:{ex}")

if __name__ == '__main__':
    url = "https://xxxx/query?leftTicketDTO.train_no=6e000D402202&leftTicketDTO.train_date=2025-02-14&rand_code="
    RequestHeader="""
    GET /otn/queryTrainInfo/query?leftTicketDTO.train_no=6e000D402202&leftTicketDTO.train_date=2025-02-14&rand_code= HTTP/1.1
    Accept: */*
Accept-Encoding: gzip, deflate, br, zstd
Accept-Language: zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6
Connection: keep-alive
Cookie: JSESSIONID=3C843B300AF2985CE9CDC31F5271E223; _jc_save_wfdc_flag=dc; _jc_save_fromStation=%u8087%u5E86%u4E1C%2CFCQ; _jc_save_toStation=%u6B66%u6C49%u4E1C%2CLFN; _jc_save_toDate=2025-01-19; BIGipServerotn=1977155850.24610.0000; BIGipServerpassport=887619850.50215.0000; guidesStatus=off; highContrastMode=defaltMode; cursorStatus=off; route=9036359bb8a8a461c164a04f8f50b252; _jc_save_fromDate=2025-02-14
Host: kyfw.12306.cn
Referer: https://kyfw.12306.cn/otn/queryTrainInfo/init
Sec-Fetch-Dest: empty
Sec-Fetch-Mode: cors
Sec-Fetch-Site: same-origin
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/132.0.0.0 Safari/537.36 Edg/132.0.0.0
X-Requested-With: XMLHttpRequest
sec-ch-ua: "Not A(Brand";v="8", "Chromium";v="132", "Microsoft Edge";v="132"
sec-ch-ua-mobile: ?0
sec-ch-ua-platform: "Windows"
    """
    result = GetRequest(url,RequestHeader)#返回一个py字典
    dataList = result["data"]["data"]#依次选择key,就可以获得对应的值
    print(dataList[0])#尝试输出第一个值
相关推荐
IVEN_6 小时前
只会Python皮毛?深入理解这几点,轻松进阶全栈开发
python·全栈
Ray Liang7 小时前
用六边形架构与整洁架构对比是伪命题?
java·python·c#·架构设计
AI攻城狮7 小时前
如何给 AI Agent 做"断舍离":OpenClaw Session 自动清理实践
python
千寻girling7 小时前
一份不可多得的 《 Python 》语言教程
人工智能·后端·python
AI攻城狮10 小时前
用 Playwright 实现博客一键发布到稀土掘金
python·自动化运维
曲幽11 小时前
FastAPI分布式系统实战:拆解分布式系统中常见问题及解决方案
redis·python·fastapi·web·httpx·lock·asyncio
孟健1 天前
Karpathy 用 200 行纯 Python 从零实现 GPT:代码逐行解析
python
码路飞1 天前
写了个 AI 聊天页面,被 5 种流式格式折腾了一整天 😭
javascript·python
曲幽1 天前
FastAPI压力测试实战:Locust模拟真实用户并发及优化建议
python·fastapi·web·locust·asyncio·test·uvicorn·workers