爬虫：百度贴吧_python吧

import urllib.request
import urllib.parse
import os


def create_request(barname,page,base_url):
    headers = {
        'User-Agent': 'Mozilla / 5.0(Windows NT 6.1;WOW64) AppleWebKit / 537.36 (KHTML, likeGecko) Chrome / 65.0.3325.146 Safari / 537.36'
    }
    p = (page - 1) * 50
    data = {
        'kw': barname,
        'pn': p
    }
    data = urllib.parse.urlencode(data)
    url = base_url + data
    request = urllib.request.Request(url=url, headers=headers)
    return request


def request_data(request):
    return urllib.request.urlopen(request)


def parse_response(response):
    return response.read().decode('utf-8')


def save_data(content,file_path,file_name):
    path = os.path.join(file_path,file_name)
    try:
        with open(path,'w',encoding='utf-8') as fp:
            fp.write(content)
    except Exception as e:
        print(e)
    else:
        print(file_name + '保存成功')


if __name__ == "__main__":
    barname = input('请输入要查询的吧名')
    start_page = int(input('请输入起始页'))
    end_page = int(input('请输入结束页'))
    base_url = 'http://tieba.baidu.com/f?'
    for page in range(start_page,end_page+1):
        # 创建一个请求对象
        request = create_request(barname,page,base_url)
        # 处理请求任务
        response = request_data(request)
        # 数据解析
        content = parse_response(response)
        # 实现本地化存储
        file_name = str(page) + '.html'
        file_path = 'tieba'
        save_data(content,file_path,file_name)
    print('全部保存成功')