17k小说网爬取书架中的小说

1. 
   
2. import requests
   
3. from lxml import etree
   
4. import os
   
5. headers  = {
   
6.         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
   
7.         }
   
8. session = requests.session()
   
9. 
   
10. def login():
    
11.     session.post("https://passport.17k.com/ck/user/login",data={
    
12.                             "loginName": "账号",
    
13.                             "password": "密码"
    
14.                     },headers=headers)
    
15. 
    
16. 
    
17. def get_shelf_books():
    
18.     '''
    
19. 
    
20.     :return:
    
21.     '''
    
22.     res = session.get("https://user.17k.com/ck/author2/shelf?page=1&appKey=2406394919")
    
23.     res.encoding="utf8"
    
24.     data = res.json().get("data")
    
25.     return data
    
26. 
    
27. 
    
28. def get_books(data):
    
29. 
    
30.     for bookDict in data:
    
31.         # print(bookDict)
    
32.         bookID = bookDict.get("bookId")
    
33.         bookName = bookDict.get("bookName")
    
34.         book_path = os.path.join(root_path,bookName)
    
35.         if not os.path.exists(book_path):
    
36.             os.mkdir(book_path)
    
37.         get_chapter(bookID,book_path,bookName)
    
38. def get_chapter(bookID,book_path,bookName):
    
39.     res = requests.get(f"https://www.17k.com/list/{bookID}.html")
    
40.     # print("res",res)
    
41.     res.encoding = "utf8"
    
42. 
    
43.     selector = etree.HTML(res.text)
    
44.     items = selector.xpath('//dl[@class="Volume"]/dd/a')
    
45.     # print(items)
    
46. 
    
47. 
    
48.     for item in items:
    
49.         chapter_href = item.xpath('./@href')[0]
    
50.         chapter_title = item.xpath('./span/text()')[0].strip()
    
51.         print("chapter_href", chapter_href)
    
52.         print("chapter_text", chapter_title)
    
53. 
    
54.         res = requests.get("https://www.17k.com" chapter_href)
    
55.         res.encoding = "utf8"
    
56.         chapter_html = res.text
    
57.         print(chapter_html)
    
58.         selector = etree.HTML(res.text)
    
59.         chapter_text = selector.xpath('//div[contains(@class,"content")]/div[@class="p"]/p[position()<last()]/text()')
    
60.         # ret = selector.xpath('//div[contains(@class,"content")]/div[@class="p"]/p[position()<last()]/text()')
    
61.         print(chapter_text)
    
62.         download(book_path, chapter_title,chapter_text)
    
63. 
    
64.         print(f'{bookName}书籍的{chapter_title}章节已经下载完成')
    
65. 
    
66. def download(book_path, chapter_title,chapter_text):
    
67.     chapter_path = os.path.join(book_path, chapter_title)
    
68.     with open(chapter_path, "w", encoding="utf8") as f:
    
69.         for line in chapter_text:
    
70.             f.write(line "\n")
    
71. 
    
72. login()
    
73. data = get_shelf_books()
    
74. root_path = "我的书架"
    
75. if  not os.path.exists(root_path):
    
76.     os.mkdir(root_path)
    
77. 
    
78. get_books(data)

复制代码

太生气了，无法HOLD啦 >_<......

66666666666666

强烈支持楼主ing……

感恩无私的分享与奉献 :)

楼主加油，我们都看好你哦。

66666666666666

激动人心，无法言表！

感恩无私的分享与奉献 :)

楼主我爱你！