本文实例为大家分享了python抓取网页中链接的静态图片的具体代码,供大家参考,具体内容如下
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
36
37
38
39
40
41
|
# -*- coding:utf-8 -*- #http://tieba.baidu.com/p/2460150866 #抓取图片地址 from bs4 import BeautifulSoup import urllib.request from time import sleep html_doc = "http://tieba.baidu.com/p/2460150866" def get_image(url): req = urllib.request.Request(url) webpage = urllib.request.urlopen(req) html = webpage.read() soup = BeautifulSoup(html, 'html.parser' ) #抓取图片地址 #抓取img标签且class为BDE_Image的所有内容 img_src = soup.findAll( "img" ,{ 'class' : 'BDE_Image' }) i = 1 for img in img_src: img_url = img.get( 'src' ) #抓取src # 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 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 |
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持服务器之家。
原文链接:http://blog.csdn.net/shentong1/article/details/79108279