python采集百度贴吧图片并保存到本地

请确保D盘有一个 image文件夹 用于存放采集到的图片
import requestsfrom lxml import etreeimport time class Baiduspider(object): def __init__(self): self.baseurl = 'https://tieba.baidu.com/' self.url = 'https://tieba.baidu.com/f?' self.headers = {'User-Agent':'Mozilla/5.0'} #获取帖子链接 def getPageUrl(self,url): res = requests.get(url,headers=self.headers) res.encoding= 'utf-8' html = res.text parseHtml = etree.HTML(html) # 2. 解析对象调用xpath r1 = parseHtml.xpath('//div[@class="t_con cleafix"]/div/div/div/a/@href') for t in r1: self.getImaUrl(t) #获取帖子中图片的连接 def getImaUrl(self,t): res = requests.get(self.baseurl t,headers=self.headers) res.encoding= 'utf-8' html = res.text parseHtml = etree.HTML(html) # 2. 解析对象调用xpath. 两个解析式不确定, 第一个不能用就换第二个 r2 = parseHtml.xpath('//div[@class="d_post_content j_d_post_content clearfix"]/img[@class="BDE_Image"]/@src') #r2 = parseHtml.xpath('//div[@class="d_post_content j_d_post_content "]/img[@class="BDE_Image"]/@src') for i in r2: self.saveImage(i) #保存图片到本地 def saveImage(self,i): print(i) res = requests.get(i,headers=self.headers) html = res.content # 这里自定义图片保存路径, 我是在d盘创建了一个image文件夹用来保存, 图片名就用time.time来定义了 with open('D:\image\%s.jpg'% time.time(),'wb') as f: f.write(html) def workOn(self): key = input('请输入要爬取的贴吧名:') pn = int(input('请输入要爬取的页数:')) for x in range(1,pn 1): url = self.url 'kw=' key '&pn=' str((x-1)*50) print('================') print(url) self.getPageUrl(url) if __name__=='__main__': spider = Baiduspider() spider.workOn()