看有人需要下百度文库的源码,来这有一份

yjsx86

1. import requests
   
2. import re
   
3. import json
   
4. import os
   
5. 
   
6. session = requests.session()
   
7. 
   
8. 
   
9. def fetch_url(url):
   
10.     return session.get(url).content.decode('gbk')
    
11. 
    
12. 
    
13. def get_doc_id(url):
    
14.     return re.findall('view/(.*).html', url)[0]
    
15. 
    
16. 
    
17. def parse_type(content):
    
18.     return re.findall(r"docType.*?:.*?\'(.*?)\',", content)[0]
    
19. 
    
20. 
    
21. def parse_title(content):
    
22.     return re.findall(r"title.*?:.*?\'(.*?)\',", content)[0]
    
23. 
    
24. 
    
25. def parse_doc(content):
    
26.     result = ''
    
27.     url_list = re.findall('(https.*?0.json.*?)\\\\x22}', content)
    
28.     url_list = [addr.replace("\\\\\\/", "/") for addr in url_list]
    
29.     for url in url_list[:-5]:
    
30.         content = fetch_url(url)
    
31.         y = 0
    
32.         txtlists = re.findall('"c":"(.*?)".*?"y":(.*?),', content)
    
33.         for item in txtlists:
    
34.             if not y == item[1]:
    
35.                 y = item[1]
    
36.                 n = '\n'
    
37.             else:
    
38.                 n = ''
    
39.             result += n
    
40.             result += item[0].encode('utf-8').decode('unicode_escape', 'ignore')
    
41.     return result
    
42. 
    
43. 
    
44. def parse_txt(doc_id):
    
45.     content_url = 'https://wenku.baidu.com/api/doc/getdocinfo?callback=cb&doc_id=' + doc_id
    
46.     content = fetch_url(content_url)
    
47.     md5 = re.findall('"md5sum":"(.*?)"', content)[0]
    
48.     pn = re.findall('"totalPageNum":"(.*?)"', content)[0]
    
49.     rsign = re.findall('"rsign":"(.*?)"', content)[0]
    
50.     content_url = 'https://wkretype.bdimg.com/retype/text/' + doc_id + '?rn=' + pn + '&type=txt' + md5 + '&rsign=' + rsign
    
51.     content = json.loads(fetch_url(content_url))
    
52.     result = ''
    
53.     for item in content:
    
54.         for i in item['parags']:
    
55.             result += i['c'].replace('\\r', '\r').replace('\\n', '\n')
    
56.     return result
    
57. 
    
58. 
    
59. def parse_other(doc_id):
    
60.     content_url = "https://wenku.baidu.com/browse/getbcsurl?doc_id=" + doc_id + "&pn=1&rn=99999&type=ppt"
    
61.     content = fetch_url(content_url)
    
62.     url_list = re.findall('{"zoom":"(.*?)","page"', content)
    
63.     url_list = [item.replace("\", '') for item in url_list]
    
64.     if not os.path.exists(doc_id):
    
65.         os.mkdir(doc_id)
    
66.     for index, url in enumerate(url_list):
    
67.         content = session.get(url).content
    
68.         path = os.path.join(doc_id, str(index) + '.jpg')
    
69.         with open(path, 'wb') as f:
    
70.             f.write(content)
    
71.     print("图片保存在" + doc_id + "文件夹")
    
72. 
    
73. 
    
74. def save_file(filename, content):
    
75.     with open(filename, 'w', encoding='utf8') as f:
    
76.         f.write(content)
    
77.         print('已保存为:' + filename)
    
78. 
    
79. 
    
80. def main():
    
81.     url = input('请输入要下载的文库URL地址_')
    
82.     content = fetch_url(url)
    
83.     doc_id = get_doc_id(url)
    
84.     Type = parse_type(content)
    
85.     title = parse_title(content)
    
86.     if Type == 'doc':
    
87.         result = parse_doc(content)
    
88.         save_file(title + '.txt', result)
    
89.     elif Type == 'txt':
    
90.         result = parse_txt(doc_id)
    
91.         save_file(title + '.txt', result)
    
92.     else:
    
93.         parse_other(doc_id)
    
94. 
    
95. 
    
96. if __name__ == "__main__":
    
97.     main()

复制代码

ApkB

战略性标记

吃货

mark

漂移弟

战略mark

nogcp

战略性mark

shares

看见了
下载的是图片
如果能是源文档就完美了
还是谢谢了

seek0515

不是可以直接下载原文档吗

bbsdamin

楼主666啊，标记一下

maiawpyg

来个教程啊