1、爬虫入门程序

urllib2 实现下载网页的三种方式

print "第二种方法"
request = urllib2.Request(url)
#模拟Mozilla浏览器进行爬虫
request.add_header("user-agent","Mozilla/5.0")
response2 = urllib2.urlopen(request)
print response2.getcode()
print len(response2.read())

print "第三种方法"
cookie = cookielib.CookieJar()
#加入urllib2处理cookie的能力
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
urllib2.install_opener(opener)
response3 = urllib2.urlopen(url)
print response3.getcode()
print len(response3.read())
print cookie

使用 Beautiful Soup 解析 html 文件


#!/usr/bin/python
# -*- coding: UTF-8 -*-
 
import re
 
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>
<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>


#创建一个BeautifulSoup解析对象
soup = BeautifulSoup(html_doc,"html.parser",from_encoding="utf-8")
#获取所有的链接
links = soup.find_all('a')
print "所有的链接"
for link in links:
    print link.name,link['href'],link.get_text()
 
print "获取特定的URL地址"
link_node = soup.find('a',href="http://example.com/elsie")
print link_node.name,link_node['href'],link_node['class'],link_node.get_text()
 
print "正则表达式匹配"
link_node = soup.find('a',href=re.compile(r"ti"))
print link_node.name,link_node['href'],link_node['class'],link_node.get_text()
 
print "获取P段落的文字"
p_node = soup.find('p',class_='story')
print p_node.name,p_node['class'],p_node.get_text()

2.爬虫程序添加header，然后post请求

设置Header代码

import urllib  
import urllib2  
 
url = 'http://www.server.com/login'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'  
values = {'username' : 'cqc',  'password' : 'XXXX' }  
headers = { 'User-Agent' : user_agent }  
data = urllib.urlencode(values)  
request = urllib2.Request(url, data, headers)  
response = urllib2.urlopen(request)  
page = response.read()

post方式

import urllib
import urllib2
 
values = {"username":"1016903103@qq.com","password":"XXXX"}
data = urllib.urlencode(values) 
url = "https://passport.csdn.net/account/login?from=http://my.csdn.net/my/mycsdn"
request = urllib2.Request(url,data)
response = urllib2.urlopen(request)
print response.read()

3、爬虫程序添加cookie

利用 cookie 模拟网站登录

import urllib
import urllib2
import cookielib
 
filename = 'cookie.txt'
#声明一个MozillaCookieJar对象实例来保存cookie，之后写入文件
cookie = cookielib.MozillaCookieJar(filename)
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
postdata = urllib.urlencode({
			'stuid':'201200131012',
			'pwd':'23342321'
		})
#登录教务系统的URL
loginUrl = 'http://jwxt.sdu.edu.cn:7890/pls/wwwbks/bks_login2.login'
#模拟登录，并把cookie保存到变量
result = opener.open(loginUrl,postdata)
#保存cookie到cookie.txt中
cookie.save(ignore_discard=True, ignore_expires=True)
#利用cookie请求访问另一个网址，此网址是成绩查询网址
gradeUrl = 'http://jwxt.sdu.edu.cn:7890/pls/wwwbks/bkscjcx.curscopre'
#请求访问成绩查询网址
result = opener.open(gradeUrl)
print result.read()

4.正则表达式

. 表示任何单个字符
[ ] 字符集，对单个字符给出取值范围
[^ ] 非字符集，对单个字符给出排除范围
* 前一个字符0次或无限次扩展
+ 前一个字符1次或无限次扩展
? 前一个字符0次或1次扩展
| 左右表达式任意一个
{m} 扩展前一个字符m次
{m,n} 扩展前一个字符m至n次（含n）
^ 匹配字符串开头
$ 匹配字符串结尾
( ) 分组标记，内部只能使用| 操作符
\d 数字
\w 单词字符

原文地址：https://blog.csdn.net/m0_64681598/article/details/123600131

爬虫基础