初学用python写爬虫, 这里分享给大家一段爬取百度贴吧的代码(用面向对象的思想写的),请各位大佬们指点迷津

百度贴吧爬虫小程序

import os
import urllib.request
import urllib.parse

class BaiduTiebaSpider(object):
def init(self, tieba_name, page):
‘’’
初始化必要参数,完成基础设置
:param tieba_name:
:param page:
‘’’
self.base_url = 'https://tieba.baidu.com/f?’
self.tieba_name = tieba_name
self.page = page
self.headers = {
‘User-Agent’: ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36’,

    }

def make_url(self):
    '''
    制作url,
    :return:
    '''
    base_url = 'https://tieba.baidu.com/f?'
    url_list = []
    for p in range(1, self.page + 1):
        pn = (p - 1) * 50
        data = {
            'kw': self.tieba_name,
            'ie': 'utf-8',
            'pn': pn
        }
        query_string = urllib.parse.urlencode(data)
        url = base_url + query_string
        url_list.append(url)
    # print(url_list)

    return url_list

def request(self, url):
    '''
    发送请求对象,获取响应
    :return:
    '''
    # 创建请求对象
    request = urllib.request.Request(url=url, headers=self.headers)
    response = urllib.request.urlopen(request)
    content = response.read()
    return content

def keep(self, text, page_num):
    """
    保存文件
    :return:
    """
    if not os.path.exists(self.tieba_name):
        os.mkdir('%s' % self.tieba_name)

    filename = '%s_第%s页.html' % (self.tieba_name, page_num)
    dirname = '%s' % self.tieba_name
    filepath = os.path.join(dirname, filename)
    with open(filepath, 'wb') as f:
        f.write(text)

def run(self):
    '''
    启动文件
    :return:
    '''
    # print(self.make_url())
    url_list = self.make_url()
    for url in url_list:
        text = self.request(url)
        page_num = url_list.index(url) + 1
        self.keep(text, page_num)

if name == ‘main’:
xiaodu = BaiduTiebaSpider(‘lol’, 5)
xiaodu.run()

发布了4 篇原创文章 · 获赞 3 · 访问量 6758
展开阅读全文

没有更多推荐了,返回首页

©️2019 CSDN 皮肤主题: 大白 设计师: CSDN官方博客

分享到微信朋友圈

×

扫一扫,手机浏览