Python爬虫_糗事百科

本爬虫任务：

爬虫糗事百科网站（https://www.qiushibaike.com/）——段子版块中所有的【段子】、【投票数】、【神回复】等内容

步骤：

1. 通过翻页寻找url规律，构造url列表
2. 查看审查元素，发现网页内容均在elements中，可以直接请求
3. 通过xpath提取需要的内容
4. 保存数据

逻辑：

• 构造外层url列表并进行遍历
  • 对外层url请求访问，获得响应
  • 提取内层url列表
  • 遍历内层url
    • 对内层url请求访问，获取响应
    • 提取需要的数据（段子、投票数、神回复）
    • 保存

代码：

 1 import requests
 2 from lxml import etree
 3 import json
 4
 5
 6 class QiuShiSpider:
 7     def __init__(self):
 8         self.start_url = "https://www.qiushibaike.com/text/page/{}/"
 9         self.headers = {
10             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.k36 (KHTML, like Gecko) ""Chrome/86.0.4240.11"}
11
12     def parse_url(self, url):
13         res = requests.get(url, headers=self.headers)
14         return res.content.decode()
15
16     def get_urls_inner(self, html_str):
17         html = etree.HTML(html_str)
18         urls_inner = html.xpath("//a[@class='contentHerf']/@href")
19         full_urls_inner = ["https://www.qiushibaike.com" + i for i in urls_inner]
20         return full_urls_inner
21
22     def get_contents(self, html_str):
23         html = etree.HTML(html_str)
24         text_list = html.xpath("//div[@class='content']/text()")
25         text = "".join(text_list)
26         number = html.xpath("//span[@class='stats-vote']/i/text()")[0] if len(
27             html.xpath("//span[@class='stats-vote']/i/text()")) > 0 else None
28         main_text_list = html.xpath("//div/span[@class='body']/text()")
29         return text, number, main_text_list
30
31     def save(self, content_dic):
32         with open("qs4.txt", "a", encoding="utf-8") as f:
33             f.write(json.dumps(content_dic, ensure_ascii=False, indent=2))
34
35     def run(self):
36         # 遍历url发送请求获取响应
37         urls_outer = [self.start_url.format(n + 1) for n in range(13)]
38         for url_outer in urls_outer:
39             try:
40                 html_str = self.parse_url(url_outer)
41                 urls_inner = self.get_urls_inner(html_str)
42                 for url_inner in urls_inner:
43                     content_dic = {}
44                     html_str = self.parse_url(url_inner)
45                     text, number, main_text_list = self.get_contents(html_str)
46                     content_dic["text"] = text
47                     content_dic["number"] = number
48                     content_dic["main_text"] = main_text_list
49
50                     self.save(content_dic)
51                     print("第{}页，第{}条".format(urls_outer.index(url_outer), urls_inner.index(url_inner)))
52             except Exception as e:
53                 print(e)
54
55
56 if __name__ == "__main__":
57     qs = QiuShiSpider()
58     qs.run()