【python 爬虫】百度贴吧帖子所有楼层图片爬虫

下载百度贴吧帖子图片,好好看
这里写图片描述

python2.7版本:

#coding=utf-8
import re
import requests
import urllib
from bs4 import BeautifulSoup
import time
time1=time.time()
def getHtml(url):
    page = requests.get(url)
    html =page.text
    return html

def getImg(html):
    soup = BeautifulSoup(html, 'html.parser')
    img_info = soup.find_all('img', class_='BDE_Image')
    global index
    for index,img in enumerate(img_info,index+1):
        print ("正在下载第{}张图片".format(index))
        urllib.urlretrieve(img.get("src"),'C:/pic4/%s.jpg' % index)

def getMaxPage(url):
    html = getHtml(url)
    reg  = re.compile(r'max-page="(\d+)"')
    page = re.findall(reg,html)
    page = int(page[0])
    return page


if __name__=='__main__':
    url   = "https://tieba.baidu.com/p/5113603072"
    page  = getMaxPage(url)
    index = 0
    for i in range(1,page):
        url = "%s%s"  % ("https://tieba.baidu.com/p/5113603072?pn=",str(i))
        html = getHtml(url)
        getImg(html)

    print ("OK!All DownLoad!")

    time2=time.time()
    print u'总共耗时:' + str(time2 - time1) + 's'
已标记关键词 清除标记
©️2020 CSDN 皮肤主题: 编程工作室 设计师:CSDN官方博客 返回首页