python(爬虫基础贴吧)

 

    from urllib import request, parse, error
    import json
    import time
    import os
    class post_bar():
        def creeper(self, name, page, path):
            base_url = 'https://tieba.baidu.com/f?kw={}&ie=utf-8&pn={}'
            head = {
                'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'
            }
            try:
                path1 = os.path.join(path,name)  
                if not os.path.exists(path1):  
                    os.mkdir(path1)    # 创建文件夹
                for i in range(page):
                    i = i * 50        # 贴吧每页帖子数量为50
                    name1 = parse.quote(name)    # 将中文转码
                    base_url1 = base_url.format(name1, i)  
                    response = request.Request(base_url1, headers=head)
                    response = request.urlopen(response)
                    response1 = response.read().decode("utf-8")
                     
                    print(path1)
                    with open(path1 + "//" +name + str(i) + '.html', 'w',encoding="utf-8") as e:
                            e.write(response1)       # 将获取到的页面写入路径中
            except error.HTTPError as e:
                    print(e.code)        # 获取报错代码
            except error.URLError as e:
                    print(e.reason)      # 获取报错原因
    file = os.getcwd()[0:-5]             # 获取当前路径
    tieba = post_bar()                   # 实例化对象
    tieba.creeper(名字, 页数, 路径)      # 调用函数