python爬虫爬取百度贴吧——高考吧图片

话不多说，直接上代码。

mport urllib.request
import re
from lxml import etree

def gethtml(start):
    #str(start)=0表示第一页，50表示第二页，……。
    url = 'http://tieba.baidu.com/f?kw=%E9%AB%98%E8%80%83&ie=utf-8&pn='+str(start)+''
    page = urllib.request.urlopen(url).read()
    html = etree.HTML(page)
    imglink =html.xpath('//div[@class="threadlist_title pull_left j_th_tit "]/a/@href')
    for i in imglink:
        # print(i)
        get_son_html(page,i)

def get_son_html(page,i):
    son_page = urllib.request.urlopen('http://tieba.baidu.com'+i).read().decode('utf-8')
    getimg(son_page,i)

def getimg(son_page,i):
    x=1
    path = 'F:\\baidutieba\\'
    reg = r'src="(http://imgsrc.*?\.jpg)"'
    imgre = re.compile(reg)
    imglist = re.findall(imgre,son_page)
    list = filter(None,imglist)
    for i in list:
        x=1
        img = urllib.request.urlopen(i)
        imgresp = img.read()
        pic = open(path+i.split('/')[-1],'wb')
        pic.write(imgresp)
        x+=1
    print('正在保存……')

if __name__=='__main__':
    for n in range(0,5):
     gethtml(start=n*50)