Python 爬虫2

import urllib.request
import os
import re
import time

设置头文件

head={}
head['User-Agent'] ='Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.75 Safari/537.36'

主要是用来查看测试是否可以访问网页，并取回源码

def url_open(url):
    req=urllib.request.Request(url,headers=head)
    response=urllib.request.urlopen(req)
    html=response.read()
    return html

每一个车模有一个ID，每个ID在网站的中的图片数量不同，此函数主要是取回每个ID下有多少张图片

def get_page_num(url):
    html=url_open(url).decode('gbk')
    html=str(html)
    text=[]
    a =html.find(r'<div class="content-page"><span class="page-ch">')
    b =html[a+49:a+51]
    mode=re.compile(r'\d+')
    page_num=mode.findall(b)
    return page_num

取回车模的ID号

def find_ID_num(url):

    html=url_open(url).decode('gb2312')
    ID_num=[]
    a =html.find('src=')
    while a!=-1:
        b=html.find('.jpg',a,a+255)
        if b!=-1:
            c=html[a+5:b+4]
            an=re.match('http://img1.mm131.com/pic/',c)
            if an!=None:
                c=c.split('/')[-2]
                ID_num.append(c)
            else:
                pass
        else:
            b=a+5

        a=html.find('src=',b)

    return ID_num

生成图片原地址，并存放在列表pic_addrs[]中

def ID_web(url):
    pic_addrs=[]
    ID_num=find_ID_num(url)
    i=0
    while i <len(ID_num):

        url1=url+str(ID_num[i])+'.html'
        page_num=get_page_num(url1)
        pic_page=2
        while pic_page<int(page_num[0])+1:
            pic_addr='http://img1.mm131.com/pic/'+str(ID_num[i])+'/'+str(pic_page)+'.jpg'
            pic_addrs.append(pic_addr)
            pic_page+=1

        i+=1

    return pic_addrs

访问图片原地址，生成本地文件并给图片命名

def save_imgs(folder,pic_addrs):
    for each in pic_addrs:
        filename=each.split('com/')[-1].replace('/','_')

        with open(filename,'wb') as f:
            img=url_open(each)
            f.write(img)
            time.sleep(5)

主函数

def download_mm(folder="OOXXmm1"):
    os.chdir(folder)
    url="http://www.mm131.com/chemo/"
    pic_addrs=ID_web(url)
    save_imgs(folder,pic_addrs)

if __name__=='__main__':
    download_mm()