1、# -*- coding:utf-8 -*-#http://tieba.baidu.com/p/2460150866#抓取图片地址from bs4 import BeautifulSoupimport urllib.requestfrom time import sleep
2、html_doc 屏顿幂垂= "http://tieba.baidu.com/p/2460150866"def 爿讥旌护get_image(url):req = urllib.request.Request(url)webpage = urllib.request.urlopen(req)html = webpage.read()soup = BeautifulSoup(html, 'html.parser')
3、抓取图片地址抓取img标签且class为BDE_Image的所有内容
4、# print(img)req = urllib.request.Request(img_url)u = urllib.request.urlopen(req)data = u.read()with open("AutoCodePng20180119-"+str(i)+".jpg", 'wb') as f:sleep(2)f.write(data)i += 1
5、def getImg(url):html = urllib.request(url)page = html.read()soup = BeautifulSoup(page, "html.parser")imglist = soup.find_all('img') #发现html中带img标签的数据，输出格式为<img xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx，存入集合lenth = len(imglist) #计算集合的个数for i in range(lenth):print imglist[i].attrs['src'] #抓取img中属性为src的信息,例如<img src="123456" xxxxxxxxxxxxxxxx,则输出为123456
6、这样，python就把静态网页转换为图片了，以上内容希望可以对大家解决问题有所帮助哟，可以试一下~
