requests获取响应

# coding=utf-8

import requests
from urllib import parse

headers = {
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:79.0) Gecko/20100101 Firefox/79.0"
}
p = {"wd": "太阳"}

url = "https://www.baidu.com/s?"

r = requests.get(url=url, headers=headers, params=p)

print(r.status_code)
print(r.request.url)    # 获得编码字符串
print(parse.unquote(r.request.url))     # 获得解码字符串

运行结果:

实例应用

要求: 实现任意贴吧的爬虫,保存网页到本地!

我们以爬取lol贴吧为例, 爬取内容;

 程序:

# coding=utf-8

# 爬取百度贴吧的内容

import requests
class TieBaSpider:
    def __init__(self, tieba_name):
        self.tieba_name = tieba_name
        self.url_temp = "https://tieba.baidu.com/f?kw=" + tieba_name + "&ie=utf-8&pn={}"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}

    def get_url_list(self):  # 构造url列表
        # url_list = []
        # for i in range(1000):
        #     url_list.append(self.url_temp.format(i*50))   # 该贴吧页码是50的倍数
        # return url_list
        return [self.url_temp.format(i * 50) for i in range(1000)]

    def parse_url(self, url):  # 发送请求获取响应
        print(url)
        response = requests.get(url, headers=self.headers)
        return response.content.decode()


    def save_html(self, html_str, page_num):  # 保存 html字符串
        file_path = "{}-第{}页.html".format(self.tieba_name, page_num)
        with open(file_path, "w", encoding="utf-8") as f:  # '李毅-第一页.html'
            f.write(html_str)


    def run(self):  # 实现主要逻辑
        # 1.构造url列表
        url_list = self.get_url_list()
        # 2.遍历，发送请求，获取响应
        for url in url_list:
            html_str = self.parse_url(url)
            # 3.保存
            page_num = url_list.index(url) + 1  # 页码数
            self.save_html(html_str, page_num)

if __name__ == '__main__':
    tieba = TieBaSpider("lol")
    tieba.run()

运行结果: