python2与pyhton3爬取百度贴吧

使用python3和python2爬取百度贴吧数据保存到本地，仅作为python2和python3在urllib2模块使用上的区别的记录
python2版本

#coding:utf-8

# import urllib.request
import urllib2

# import urllib.parse
import urllib


class BaiduSpider(object):
    def __init__(self):
        self.base_url = "http://tieba.baidu.com/f?"
        self.headers = {"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"}

        self.tieba_name = raw_input("请输入需要抓取的贴吧：")
        self.start_page = int(raw_input("请输入需要抓取的起始页:"))
        self.end_page = int(raw_input("请输入需要抓取的结束页:"))


    def send_request(self, url):
        """ 接收url地址，发送请求返回响应"""
        print("[INFO]: 正在发送请求 : {}...".format(url))

        # 构建并发送请求
        request = urllib2.Request(url, headers=self.headers)
        response = urllib2.urlopen(request)
        # 返回响应对象
        return response


    # def parse_response(self):
    #     pass


    def save_data(self, response, file_name):
        """ 接收并保存数据到磁盘文件中 """
        print("[INFO]: 正在保存数据 {}".format(file_name))
        with open(file_name, "w") as f:
            f.write(response.read())


    def main(self):

        for page in range(self.start_page, self.end_page + 1):
            # 通过计算页码值，得出pn值
            pn = (page - 1) * 50

            # 构建查询参数字典（贴吧名，页数）
            query_dict = {"pn" : pn, "kw" : self.tieba_name}
            # 构建查询字符串
            query_str = urllib.urlencode(query_dict)

            # base_url和查询字符串拼接，构建完整的url地址
            full_url = self.base_url + query_str

            #print(full_url)
            # 发送url请求，返回响应
            response = self.send_request(full_url)

            # python强类型动态解释型语言
            # 构建当前响应的文件名
            file_name = self.tieba_name + str(page) + ".html"

            # 保存数据
            self.save_data(response, file_name)


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

python3版本

import urllib.request
import urllib.parse


class BaiduSpider(object):
    def __init__(self):
        self.base_url = "http://tieba.baidu.com/f?"
        self.headers = {"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"}

        self.tieba_name = input("请输入需要抓取的贴吧：")
        self.start_page = int(input("请输入需要抓取的起始页:"))
        self.end_page = int(input("请输入需要抓取的结束页:"))


    def send_request(self, url):
        """ 接收url地址，发送请求返回响应"""
        print("[INFO]: 正在发送请求 : {}...".format(url))

        # 构建并发送请求
        request = urllib.request.Request(url, headers=self.headers)
        response = urllib.request.urlopen(request)
        # 返回响应对象
        return response


    # def parse_response(self):
    #     pass


    def save_data(self, response, file_name):
        """ 接收并保存数据到磁盘文件中 """
        print("[INFO]: 正在保存数据 {}".format(file_name))
        with open(file_name, "wb") as f:
            f.write(response.read())


    def main(self):

        for page in range(self.start_page, self.end_page + 1):
            # 通过计算页码值，得出pn值
            pn = (page - 1) * 50

            # 构建查询参数字典（贴吧名，页数）
            query_dict = {"pn" : pn, "kw" : self.tieba_name}
            # 构建查询字符串
            query_str = urllib.parse.urlencode(query_dict)

            # base_url和查询字符串拼接，构建完整的url地址
            full_url = self.base_url + query_str

            #print(full_url)
            # 发送url请求，返回响应
            response = self.send_request(full_url)

            # python强类型动态解释型语言
            # 构建当前响应的文件名
            file_name = self.tieba_name + str(page) + ".html"

            # 保存数据
            self.save_data(response, file_name)


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

新手学习的话运行测试看看区别，下次给爬取贴吧图片的代码