Skip to content
Navigation Menu
Sign in
Products
Platform
GitHub
Repository hosting, code review, and collaboration
Copilot
AI coding agent for tasks, projects, and automated work
Build & Ship
Actions
CI/CD and automation
Code Quality
Quality analysis, fixes, and enforcement
Codespaces
Cloud development environments
Secure
Code Security
Vulnerability detection and remediation
Secret Protection
Secret scanning and leak prevention
All Features
Developers
Learn
Documentation
Training
Certifications
Build
Build with Copilot
Customize Copilot
Integrations
Explore
Trending repos
GitHub Sponsors
Developer articles
Changelog
Changelog
Your source for the latest features, improvements, and fixes across GitHub products, all in one place.
Businesses
By Stage
Enterprises
Team
Startups
Nonprofits
By Industry
Healthcare
Financial services
Manufacturing
Government
See all industries
Evaluate GitHub
Why GitHub
Customer Stories
Business insights
Trust Center
Add-ons
GitHub Advanced Security
Enterprise-grade code security
Copilot for business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Resources
Learn & Connect
Documentation
Resource center
Blog
Events & webinars
Community Forum
Customer Stories
Integrations
Support
Customer support
Training
GitHub Status
Company
About
Partners
Changelog
GitHub Universe
GitHub Universe
The event for developers, by developers — talks, workshops, and what’s next for GitHub.
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
hkanyx
PythonDemo
Repository navigation
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
More
items
Files
Expand file tree
master
Breadcrumbs
PythonDemo
/
pc5.py
Copy path
Blame
More file actions
Blame
More file actions
Latest commit
History
History
History
38 lines (31 loc) · 1.93 KB
master
Breadcrumbs
PythonDemo
/
pc5.py
Copy path
Top
File metadata and controls
Code
Blame
38 lines (31 loc) · 1.93 KB
Raw
Copy raw file
Download raw file
Open symbols panel
Edit and raw actions
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
#-*- coding:utf-8 -*- http://www.aichengxu.com
import urllib2
import re
import requests
from lxml import etree
links=[]
k=1
print u'请输入最后的页数:'
endPage=int(raw_input()) #最终的页数 (r'\d+(?=\s*页) 这是一个比较通用的正则抓取总页数的代码,当然最后要group
#这里是手动输入页数,避免内容太多
for j in range(0,endPage):
url='http://tieba.baidu.com/f?kw=%E7%BE%8E%E5%A5%B3&ie=utf-8&pn='+str(j) #页数的url地址
html=urllib2.urlopen(url).read() #读取首页的内容
selector=etree.HTML(html) #转换为xml,用于在接下来识别
links=selector.xpath('//div/a[@class="j_th_tit"]/@href') #抓取当前页面的所有帖子的url
#大家可以使用浏览器自带的源码查看工具,在指定目标处查看元素,这样更快捷
for i in links:
url1="http://tieba.baidu.com"+i #因为爬取到的地址是相对地址,所以要加上百度的domain
html2=urllib2.urlopen(url1).read() #读取当前页面的内容
selector=etree.HTML(html2) #转换为xml用于识别
link=selector.xpath('//img[@class="BDE_Image"]/@src') #抓取图片,各位也可以更换为正则,或者其他你想要的内容
#此处就是遍历下载
for each in link:
#print each
print u'正在下载%d'%k
fp=open('image/'+str(k)+'.bmp','wb') #下载在当前目录下 image文件夹内,图片格式为bmp
image1=urllib2.urlopen(each).read() #读取图片的内容
fp.write(image1) #写入图片
fp.close()
k+=1 #k就是文件的名字,每下载一个文件就加1
print u'下载完成!'
You can’t perform that action at this time.