记录一个Python爬虫实践

import requests
import os
from bs4 import BeautifulSoup

# 保存图片
def downloadImg(image_src):
        tempfileName=os.path.basename(image_src)
        with open (f"爬虫图片/{tempfileName}","wb") as fout:
            fout.write(requests.get(image_src).content) 
            print(f"{image_src} ok");

headers={
"user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
}

page=1
domain="https://pic.netbian.com"

while page<100:
    page+=1
    req=requests.get(f"https://pic.netbian.com/4kmeinv/index_{page}.html",headers=headers);
    req.encoding="gbk";# 解决乱码问题

    soup=BeautifulSoup(req.text,"html.parser");
    for link in soup.find_all("a"):
        if link.get("href") and "/tupian" in link.get("href"):
            tempReq=requests.get(domain+link.get("href"),headers=headers)
            tempReq.encoding="gbk"
            tempSoup=BeautifulSoup(tempReq.text,"html.parser")
            tempA= tempSoup.find(id="img")

            for tempImage in tempA.find_all("img"):
                if  tempImage.get("src") and "/uploads" in tempImage.get("src"):
                        downloadImg(domain+tempImage.get("src"))

标签：src,Python,image,爬虫,实践,537.36,fout,import,tempfileName
来源： https://blog.csdn.net/canyanol/article/details/122821749