爬取贴吧图片

Python爬虫之贴吧图片

今天我们来爬取java吧的图片，开始写代码之前先要找到页面的url，以及对应图片的url

from urllib import request
import urllib
import re
import time
from lxml import html
etree=html.etree
#https://tieba.baidu.com/f?kw=java&ie=utf-8&pn=0  第一页
#https://tieba.baidu.com/f?kw=java&ie=utf-8&pn=50  第二页
header={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) \
    AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18362'}
url=r'http://tieba.baidu.com'
class Spider():
    def __init__(self):
        self.tiebaName='java'
        self.beginPage=1
        self.endPage=1
        self.url=r'http://tieba.baidu.com/f?'
        self.fileName=1
    #获取页面的网址
    def tiebaSpider(self):
        for page in range(self.beginPage-1,self.endPage):
            pn=page*50
            kw={'kw':'java'}
            urll=urllib.parse.urlencode(kw)
            fullurl=self.url+urll+'&ie=utf-8&pn='+str(pn)
            self.tiebaText(fullurl)
    #获取页面信息
    def tiebaText(self,fullurl):
        req=request.Request(fullurl,headers=header)
        response=urllib.request.urlopen(req).read().decode()
        pat=r'href="(.*?)"(.+)target="_blank"(.+)class="j_th_tit "'
        res=re.compile(pat,re.I)
        data=res.findall(response)
        for i in range(0,len(data)):
            data1=data[i][0]
            link=url+data1
            req1=request.Request(link,headers=header)
            response1=urllib.request.urlopen(req1).read().decode()
            self.tiebaImage(response1)
    #获取图片网址,并写入本地
    def tiebaImage(self,response1):
        res=etree.HTML(response1)
        Imagelink=res.xpath('//img[@class="BDE_Image"]/@src')
        for imagelink in Imagelink:
            print(imagelink)
            image=urllib.request.urlopen(imagelink).read()
            print('正在存储图片：',self.fileName,'.........')
            f=open(r'C:\Users\lenovo\Pictures\Saved Pictures\\'+str(self.fileName)+'.jpg','wb')
            f.write(image)
            time.sleep(0.5)
            f.close()
        self.fileName+=1

if __name__=='__main__':
    mySpider=Spider()
    mySpider.tiebaSpider()

运行程序：

找到存储图片的位置，查看图片：

这样java贴吧的图片就获取成功了！！！