python爬取百度贴吧图片库_python抓取百度贴吧-校花吧，网页图片

该楼层疑似违规已被系统折叠 隐藏此楼查看此楼

#!/usr/bin/python3

#code=utf-8

import urllib.request

import re

path = "C:\\Users\\Administrator\\Pictures\\python\\816\\" #图片下载的地址

#根据网址字符串，读取网页

def getHtml(url):

page = urllib.request.urlopen(url)

html = page.read()

return html

def getUrllist(html):

#reg = r'bpic="(.+?\.jpg)"'

#imgre = re.compile(reg)

#指定编码要求

html = html.decode('utf-8')

# imglist = re.findall(imgre,html)

reg1 = r'

urlre = re.compile(reg1)

urllist = re.findall(urlre,html)

print(urllist)

return urllist

def downloadImg(urllist):

x = 0

for imgurl in urllist:

#拼接完整url

imgurl = "http://" + imgurl

print(imgurl)

imgurl = getHtml(imgurl)

#图片正则表达式

reg = r'bpic="(.+?\.jpg)"'

imgre = re.compile(reg)

try:

html = imgurl.decode('utf-8')

except Exception as err:

print(err)

#获取网页图片数组

imglist = re.findall(imgre, html)

#下载图片

for imgurl in imglist:

urllib.request.urlretrieve(imgurl, path + 'w%s.jpg' % x)

print('w%s.jpg' % x)

x += 1

'''

x = 0

for imgurl in imglist:

urllib.request.urlretrieve(imgurl,path+ '%s.jpg' % x)

x+=1

'''

html = getHtml("http://tieba.baidu.com/f?kw=%D0%A3%BB%A8&fr=ala0&tpl=5")

urllist = getUrllist(html)

downloadImg(urllist)

#异常日志输出