2021-01-19

爬优美图库

import requests
from bs4 import BeautifulSoup

headers = {"user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4098.3 Safari/537.36"}
urls = []
n = 1
for i in range(1,10):
    url ="https://www.umei.cc/meinvtupian/meinvxiezhen/{}.htm".format(i)
    urls.append(url)
#print(urls)
    for url in urls:
        content = requests.get(url,headers=headers,timeout=10)
        content.encoding = "utf-8"
        #print(content.text)

        soup = BeautifulSoup(content.text,"html.parser")
        div_list = soup.find("div",class_="TypeList").find_all("a",class_="TypeBigPics")
        for div in div_list:
            child_url = div.get("href")
            #print(child_url)
            content_1 = requests.get(child_url,headers=headers)
            content_1.encoding = "utf-8"
            #print(content_1.text)
            soup_1 = BeautifulSoup(content_1.text,"html.parser")
            jpg_src = soup_1.find_all("div",class_="ImageBody").find("a").get("src")

            #下载图片
            with open(f"{n}.jpg",mode="wb") as f:
                f.write(requests.get(jpg_src).content)
            print("一张图片下载完成")
            n += 1