爬虫——三个小实战

贴吧爬取

写代码前，构思需要的功能块；写代码时，把各个功能模块名提前写好

初始化

初始化必要参数，完成基础设置 爬取百度贴吧lol吧：爬取地址中的get参数须传递(可以指定不同主题的贴吧和页码)

• 主题名
• 初始网址
• 请求头

生成网址

生成每一页的路由地址

• 根据列表生成式生成多个页面的地址

下载

get请求给每一页的地址，爬取页面

保存

保存爬取结果到文件中，把每一页爬取结果写入到对应名字的文件中

控制流程

将以上爬取操作封装到run函数中，方便外部对象调用，以后会在此添加多线程

• 生成要爬取的每一页的路由地址
• 通过for循环遍历每一个路由地址
• 对每个路由地址进行爬取和获取页码操作，并进行保存

源码

 1 import requests
 2 
 3 class tiebaspider:
 4     def __init__(self, tieba_name_crawl):
 5         """
 6         初始化必要参数，完成基础设置
 7         爬取百度贴吧lol吧：爬取地址中的get参数须传递(可以指定不同主题的贴吧和页码)
 8         """
 9         self.tieba_name = tieba_name_crawl
10         self.url_base = 'https://tieba.baidu.com/f?kw=' + tieba_name_crawl + '&ie=utf-8&pn={}'
11         self.headers = {'user-agent': 'mozilla/5.0 (windows nt 10.0; win64; x64; rv:61.0) gecko/20100101 firefox/61.0'}
12 
13     def make_url(self):
14         """
15         生成每一页的路由地址
16         :return:(列表生成式)
17         """
18         return [self.url_base.format(i) for i in range(4)]
19 
20     def download_url(self, url_str):
21         """
22         get请求给每一页的地址，爬取页面
23         :param url_str: 每一页的路由地址
24         :return: 爬取的结果
25         """
26         result = requests.get(url_str, headers=self.headers)
27         return result.text
28 
29     def save_result(self, result, page_num):
30         """
31         保存爬取结果到文件中
32         :param result: 每一页的爬取结果
33         :param page_num: 页码，方便分类保存
34         :return: 把每一页爬取结果写入到对应名字的文件中
35         """
36         # with open('./download/lol' + str(page_num) + '.html', 'ab') as f:
37         #     f.write(result.encode('utf-8'))
38         file_path = './download/{}~第{}页.html'.format(self.tieba_name,page_num)
39         with open(file_path,'wb') as f:
40             f.write(result.encode('utf-8'))
41 
42     def run(self):
43         """
44         将以上爬取操作封装到run函数中，方便外部对象调用，以后会在此添加多线程
45         · 生成要爬取的每一页的路由地址
46         · 通过for循环遍历每一个路由地址
47         · 对每个路由地址进行爬取和获取页码操作，并进行保存
48         :return:
49         """
50         url_lists = self.make_url()
51         for url_str in url_lists:
52             result_str = self.download_url(url_str)
53             p_num = url_lists.index(url_str) + 1
54             self.save_result(result=result_str,page_num=p_num)
55 
56 if __name__ == '__main__':
57     tieba_spider = tiebaspider('lol')
58     tieba_spider.run()

 

爬取糗事百科

 1 import requests
 2 from bs4 import beautifulsoup
 3 import lxml.html
 4 
 5 class qiushispider:
 6     def __init__(self):
 7         """
 8         初始化必要参数，完成基础设置
 9         """
10         # self.tieba_name = qiushi_name_crawl
11         # https: // www.qiushibaike.com / 8
12         # hr / page / 2 /
13         self.url_base = 'https://www.qiushibaike.com/8hr/page/{}/'
14         # self.url_base = 'https://tieba.baidu.com/f?kw=' + qiushi_name_crawl + '&ie=utf-8&pn={}'
15         self.headers = {'user-agent': 'mozilla/5.0 (windows nt 10.0; win64; x64; rv:61.0) gecko/20100101 firefox/61.0'}
16 
17     def make_url(self):
18         return [self.url_base.format(i) for i in range(4)]
19 
20     def download_url(self, url_str):
21         result = requests.get(url_str, headers=self.headers)
22         #----------
23         # html = lxml.html.fromstring(result.text)
24         # html_data = html.xpath('//div[@class="content"]/span[1]/text()')
25         # data_all = []
26         # # for h in html_data:
27         # #     data_all.append(h)
28         # return html_data
29         #-----------
30         return result.text
31 
32     def save_result(self, result, page_num):
33         with open('./download/qiushi' + str(page_num) + '.html', 'ab') as f:
34             f.write(result.encode('utf-8'))
35 
36 
37 # qiushi = qiushispider()
38 # qiushi_url = qiushi.make_url()
39 # j = 1
40 # for i in qiushi_url:
41 #     qiushi_text = qiushi.download_url(url_str=i)
42 #     qiushi.save_result(result=qiushi_text, page_num=j)
43 #     j += 1

 

爬取国家信息

beautifulsoup方式

 1 import requests
 2 from bs4 import beautifulsoup
 3 class countrysoup:
 4     def __init__(self,country_name):
 5         self.country_name = country_name
 6         self.url_base = 'http://example.webscraping.com/places/default/view/{}'.format(self.country_name)
 7         self.headers = {'user-agent': 'mozilla/5.0 (windows nt 10.0; win64; x64; rv:61.0) gecko/20100101 firefox/61.0',}
 8 
 9     def download_url(self):
10         result = requests.get(self.url_base,headers=self.headers)
11         soup = beautifulsoup(result.text,'lxml')
12         tr = soup.find(attrs={'id':"places_country__row"})
13         print(tr,type(tr))
14         td = tr.find(attrs={'class':"w2p_fw"})
15         print(td,type(td))
16 
17         print(td.text)

lxml方式

 1 class countryspider:
 2     def __init__(self,country_name):
 3         self.country_name = country_name
 4         self.url_base = 'http://example.webscraping.com/places/default/view/{}'.format(self.country_name)
 5         self.headers = {'user-agent': 'mozilla/5.0 (windows nt 10.0; win64; x64; rv:61.0) gecko/20100101 firefox/61.0',}
 6 
 7     def download_url(self,url_str):
 8         result = requests.get(url_str,headers=self.headers)
 9         html = lxml.html.fromstring(result.text)
10         data_country = html.xpath('//tr[@id="places_country__row"]/td[@class="w2p_fw"]/text()')
11         data_capital = html.xpath('//tr[@id="places_capital__row"]/td[@class="w2p_fw"]/text()')
12         data_area = html.xpath('//tr[@id="places_area__row"]/td[@class="w2p_fw"]/text()')
13         data_all = ['国家：'+data_country[0],'首都：'+data_capital[0],'国土面积：'+data_area[0]]
14         return data_all
15         # print(html_data)
16 
17     def save_result(self,result):
18         print(type(result),result)
19         for r in result:
20             r = r + '\n'
21             with open('./country.txt','ab') as f:
22                 f.write(r.encode('utf-8'))
23         # with open('./country.txt','ab') as f:
24         #     f.writelines(result)
25     def run(self):
26         result = self.download_url(self.url_base)
27         self.save_result(result)
28 
29 
30 if __name__ == '__main__':
31     # c = countryspider('bolivia-27')
32     # c.run()
33     s = countrysoup('bolivia-27')
34     s.download_url()