爬豆瓣影评

 1 """
 2 获取豆瓣影评上的每条影评名字，推荐人，影评内容，所有图片
 3 """
 4 import requests
 5 from lxml import etree
 6 import json
 7 
 8 
 9 class DoubanYingpingSpider(object):
10     def __init__(self):
11         self.url_temp = "https://movie.douban.com"
12         self.headers = {
13             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36"}
14 
15     def parse_url(self, url):  # 发送请求
16         print(url)
17         response = requests.get(url, headers=self.headers)
18         return response.content.decode()
19 
20     def get_content_list(self, html_str):# 提取数据
21 
22         html = etree.HTML(html_str)
23         div_list = html.xpath("//div[@class=‘review-list chart ‘]/div")
24         page_url_list = html.xpath("//div[@class=‘paginator‘]/a/@href")
25         # print(page_url_list)
26         content_list = []
27         for div in div_list:
28             item = {}
29             item["title"] = div.xpath(".//div[@class=‘main-bd‘]/h2/a/text()")
30             item["content_url"] = div.xpath(".//div[@class=‘main-bd‘]/h2/a/@href")
31             item["author"] = div.xpath(".//header/a[@class=‘name‘]/text()")
32             item["img"], item["content"] = self.get_img_and_content_list(item["content_url"][0])
33             content_list.append(item)
34             # print(item)
35         return content_list, page_url_list
36 
37     def get_img_and_content_list(self, detail_url):  # 获取单条影评内的数据
38         # 3.1当前影评的url地址
39         # 3.2 发送请求，获取响应
40         detail_html_str = self.parse_url(detail_url)
41         html = etree.HTML(detail_html_str)
42 
43         # 3.3 提取数据
44         img = html.xpath("//div[@class=‘image-wrapper‘]/img/@src")
45         content = html.xpath("//div[@class=‘review-content clearfix‘]//text()")
46         content = "".join(content).replace(‘\n        ‘, ‘‘).replace(‘\n      ‘, ‘‘)  # list转换为str
47         # print(type(content),content)
48         return img, content
49 
50     def save_content_list(self, content_list):  # 保存
51 
52         with open("豆瓣最受欢迎的影评.txt", "a", encoding=‘utf-8‘) as f:
53             for content in content_list:
54                 f.write(json.dumps(content, ensure_ascii=False, indent=4))
55                 f.write(‘\n\n‘)
56             f.write(‘*‘ * 50 + ‘\n‘)
57         print("保存成功！")
58 
59     def run(self):  # 实现主要逻辑
60         break_signal = 0
61         page_url_temp = ‘/review/best/?start=0‘
62         while True:
63             # 1.page_url
64             page_url = self.url_temp + page_url_temp
65 
66             # 2.发送请求，获取响应
67             html_str = self.parse_url(page_url)
68 
69             # 3.提取数据
70             content_list, page_url_list = self.get_content_list(html_str)
71             #     3.1 当前影评的url地址
72             #     3.2 发送请求，获取响应
73             #     3.3 提取数据
74             # 4.保存
75             self.save_content_list(content_list)
76 
77             # 5. 构造下一页的url地址，循环1-5
78             if break_signal < len(page_url_list):
79                 page_url_temp = page_url_list[break_signal]
80                 break_signal += 1
81             else:
82                 break
83 
84 
85 if __name__ == ‘__main__‘:
86     douban_spider = DoubanYingpingSpider()
87     douban_spider.run()