Python网络爬虫（6）糗事百科图片抓取按主题名保存

最新推荐文章于 2020-09-01 17:32:31 发布

One-Shell

最新推荐文章于 2020-09-01 17:32:31 发布

阅读量647

点赞数

分类专栏： Python爬虫

本文链接：https://blog.csdn.net/GenteelDevil/article/details/54292414

版权

Python爬虫专栏收录该内容

8 篇文章 0 订阅

订阅专栏

from urllib.request import urlopen
from urllib.request import urlretrieve
from bs4 import BeautifulSoup
import requests
import re
import os
url = "http://www.qiushibaike.com/imgrank/"
path = "D:/2/"

def get_html(url):  
    session = requests.Session()  
    headers = {"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_5)AppleWebKit 537.36 (KHTML, like Gecko) Chrome","Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"}  
    req = session.get(url, headers=headers)  
    bsObj = BeautifulSoup(req.text,"html.parser")  
    return bsObj

def download_img(path,filename,link):
    if not os.path.exists(path):#检测文件夹是否存在并创建
        os.makedirs(path)
    urlretrieve(link,path + filename)#第二个参数可以加上路径
        

def get_img(bsObj,path):
    img_list = bsObj.findAll("img",{"src":re.compile("http\:\/\/pic.qiushibaike.com\/system\/pictures\/[0-9]{5}\/[0-9]{9}\/medium\/app[0-9]{9}\.jpg$")})
    #正则表达式结尾记得"$" 否则会找出其它的无用图片
    for each in img_list:
        link = each["src"]
        print(link)
        filename = each["alt"]
        print(filename)
        download_img(path,filename+".jpg",link)
if __name__ == "__main__"
    html = get_html(url)
    get_img(html,path)