python使用正则以及BS4爬取图片

使用正则以及BS4爬取图片

使用了requests库，正则表达式以及BS4来进行的一个爬虫,用了easygui进行一个简单的图形界面

import requests
import os
import re
from bs4 import BeautifulSoup
import easygui as g

def url_open(url):    
    header = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0'}
    response = requests.get(url,headers = header)
    #获取图片文件用content，文字用text
    html = response.content
    return html

def get_imgs(html):
    #调用BeautifulSoup解析html,这里用python自带的解析器,lxml解析器效率更高
    soup = BeautifulSoup(html,"html.parser")
    #用find_all方法找到包含需要的
    img = str(soup.find_all(style="margin-bottom: 10px;"))
    #用正则表达式再一次进行筛选
    p = r'src="([^"]+\.jpg)"'
    imglist = re.findall(p,img)
    return imglist

def download(folder,pages,qh):
	#把目录改变为需要保存的文件夹
    os.chdir(folder)
    x = 0
    url = r'http://www.nenml.com/12/%d'%qh
    page_num = int(pages)

   #下载每一页的内容
    for i in range(pages):
        page_num -= 1
        page_url = url + '?page=' + str(page_num)
        imglist = get_imgs(url_open(page_url))
        for each in imglist:
            filename = str(x) +'.jpg'
            x += 1
            with open(filename, 'wb') as f:
                img = url_open(each)
                f.write(img)
    g.msgbox('下载成功!')
        
#如果当成模块导入将不会执行以下内容
if__name__ == '__main__'
    folder = g.diropenbox()
    pages = g.integerbox('请输入需要下载的页数：(大于1小于10！)',lowerbound=1,upperbound = 10)
    qh = g.integerbox('请输入需要下载的刊期：',lowerbound=1,upperbound = 10000)
    download(folder,pages,qh)