from urllib import request
url = 'http://www.baidu.com/'

# 向百度发请求,得到响应对象
response = request.urlopen(url)

# 返回网页源代码
print(response.read().decode('utf-8'))

# 返回http响应码
print(response.getcode())    # 200
# 返回实际数据URL地址
print(response.geturl())    # http://www.baidu.com/

from urllib import request
url = 'http://httpbin.org/get'
headers = {'User-Agent':'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; InfoPath.3)'}
# 创建请求对象(包装请求)
req = request.Request(url=url,headers=headers)
# 发请求,获取响应对象
res = request.urlopen(req)
# 读取内容,返回网页代码
html = res.read().decode('utf-8')
print(html)

from urllib import parse
url = 'http://www.baidu.com/s"htmlcode">

from urllib import parse
query_string_dict = {'wd' : '美女',
          'pn' : '50'}
query_string = parse.urlencode(query_string_dict)
url = 'http://www.baidu.com/s"htmlcode">

from urllib import request
from urllib import parse

# 定义常用变量
word = input('请输入搜索内容:')
url = 'http://www.baidu.com/s"htmlcode">

from urllib import parse
parse.quote('美女')    # %E7%BE%8E%E5%A5%B3


urllib.parse.unquote(string)解码




from urllib import parse
result = parse.unquote('%E7%BE%8E%E5%A5%B3')
print(result)    # 美女


百度贴吧网页获取



  
输入贴吧名称
  
输入起始页
  
输入终止页
  
保存到本地文件：第1页.html、第2页.html ...

实现步骤
1、找URL规律
1、不同吧


2、不同页


第1页:http://tieba.baidu.com/f"htmlcode">

from urllib import request,parse
import time
import random

class BaiduSpider(object):
  def __init__(self):
    self.url = 'http://tieba.baidu.com/f?kw={}&pn={}'
    self.headers = {'User-Agent':'Mozilla/5.0'}

  # 获取响应
  def get_page(self,url):
    req = request.Request(url=url,headers=self.headers)
    res = request.urlopen(req)
    html = res.read().decode('utf-8')
    return html

  # 保存数据
  def write_page(self,filename,html):
    with open(filename,'w') as f:
      f.write(html)

  # 主函数
  def main(self):
    name = input('请输入贴吧名:')
    start = int(input('请输入起始页:'))
    end = int(input('请输入终止页:'))

    # 拼接URL地址,发请求
    for page in range(start,end+1):
      pn = (page-1)*50
      kw = parse.quote(name)     # url编码
      url = self.url.format(kw,pn)
      html = self.get_page(url)    # 获取响应,并保存
      filename = '{}-第{}页.html'.format(name,page)
      self.write_page(filename,html)
      print('第{}页爬取成功'.format(page)) # 提示进度
      time.sleep(random.randint(1,3))   # 控制爬取速度

if __name__ == '__main__':
  spider = BaiduSpider()
  spider.main()


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。

                                
                                

                                    python,urllib,爬虫模块 
                                
华山资源网 Design By www.eoogi.com