requests模块爬取糗事百科图片用parsel解析

实例

import requests
import parsel
import time
import os

start = time.time()     # 记录程序开始时间
"""
1，定义url，伪造headers
2，请求数据
3，解析数据
4，提取数据
5，持久化保存
"""

# 判断文件是否存在
if not os.path.exists("./image"):
    # 创建文件
    os.mkdir("./image")
    print("创建文件image成功")

# 1，定义url，伪造headers
url = "https://fm.qq.com/category/39087_38979"
headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36"
}

# 2，请求数据
response = requests.get(url=url,headers=headers).text
# 3，解析数据
sel = parsel.Selector(response)
lis = sel.css('.album-list .item')[0:-1]

count = 0
for li in lis:
    time.sleep(0.5)
    # 二次解析
    img_url = li.css("img::attr(src)").get()        # 图片url
    title = li.c