本文实例讲述了Python实现爬取百度贴吧帖子所有楼层图片的爬虫。分享给大家供大家参考,具体如下:
下载百度贴吧帖子图片,好好看
python2.7版本:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
|
#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' |
希望本文所述对大家Python程序设计有所帮助。
原文链接:https://blog.csdn.net/u013421629/article/details/77941315