├── BaiduWenkuDownloads.exe
├── README.md
└── main.py


/BaiduWenkuDownloads.exe:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/7hc/BaiduWenkuDownloads/ff20ec56ecb4b9b4b762f3d165b34a6a110cbd43/BaiduWenkuDownloads.exe


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # BaiduWenkuDownloads
 2 | <br>
 3 | 这是一个百度文库收费文档下载工具。
 4 | 
 5 | ## 使用方法：
 6 | 
 7 | 下载BaiduWenkuDownloads.exe，输入要下载的文档URL并回车。
 8 | 
 9 | ## 工具说明：
10 | 
11 | * 支持DOC,TXT,PPT,PDF下载。
12 | 
13 | * DOC和TXT保存为TXT格式。
14 | 
15 | * PDF和PPT保存为JPG格式。


--------------------------------------------------------------------------------
/main.py:
--------------------------------------------------------------------------------
 1 | import requests
 2 | import re
 3 | import sys
 4 | import json
 5 | import os
 6 | import  time
 7 | 
 8 | #根据文件决定函数
 9 | y = 0
10 | def doc(url):
11 |     doc_id = re.findall('view/(.*).html', url)[0]
12 |     html = requests.get(url).text
13 |     lists=re.findall('(https.*?0.json.*?)\\\\x22}',html)
14 |     lenth = (len(lists)//2)
15 |     NewLists = lists[:lenth]
16 |     for i in range(len(NewLists)) :
17 |         NewLists[i] = NewLists[i].replace('\\','')
18 |         txts=requests.get(NewLists[i]).text
19 |         txtlists = re.findall('"c":"(.*?)".*?"y":(.*?),',txts)
20 |         for i in range(0,len(txtlists)):
21 |             global y
22 |             print(txtlists[i][0].encode('utf-8').decode('unicode_escape','ignore'))
23 |             if y != txtlists[i][1]:
24 |                 y = txtlists[i][1]
25 |                 n = '\n'
26 |             else:
27 |                 n = ''
28 |             filename = doc_id + '.txt'
29 |             with open(filename,'a',encoding='utf-8') as f:
30 |                 f.write(n+txtlists[i][0].encode('utf-8').decode('unicode_escape','ignore').replace('\\',''))
31 |         print("DOC文档保存在"+filename)
32 | 
33 | def ppt(url):
34 |     doc_id = re.findall('view/(.*).html',url)[0]
35 |     url = "https://wenku.baidu.com/browse/getbcsurl?doc_id="+doc_id+"&pn=1&rn=99999&type=ppt"
36 |     html = requests.get(url).text
37 |     lists=re.findall('{"zoom":"(.*?)","page"',html)
38 |     for i in range(0,len(lists)):
39 |         lists[i] = lists[i].replace("\\",'')
40 |     try:
41 |         os.mkdir(doc_id)
42 |     except:
43 |         pass
44 |     for i in range(0,len(lists)):
45 |         img=requests.get(lists[i]).content
46 |         with open(doc_id+'\img'+str(i)+'.jpg','wb') as m:
47 |             m.write(img)
48 |     print("PPT图片保存在" + doc_id +"文件夹")
49 | 
50 | def txt(url):
51 |     doc_id = re.findall('view/(.*).html', url)[0]
52 |     url = "https://wenku.baidu.com/api/doc/getdocinfo?callback=cb&doc_id="+doc_id
53 |     html = requests.get(url).text
54 |     md5 = re.findall('"md5sum":"(.*?)"',html)[0]
55 |     pn = re.findall('"totalPageNum":"(.*?)"',html)[0]
56 |     rsign = re.findall('"rsign":"(.*?)"',html)[0]
57 |     NewUrl = 'https://wkretype.bdimg.com/retype/text/'+doc_id+'?rn='+pn+'&type=txt'+md5+'&rsign='+rsign
58 |     txt = requests.get(NewUrl).text
59 |     jsons = json.loads(txt)
60 |     texts=re.findall("'c': '(.*?)',",str(jsons))
61 |     print(texts)
62 |     filename=doc_id+'.txt'
63 |     with open(filename,'a',encoding='utf-8') as f:
64 |         for i in range(0,len(texts)):
65 |             texts[i] = texts[i].replace('\\r','\r')
66 |             texts[i] = texts[i].replace('\\n','\n')
67 | 
68 |             f.write(texts[i])
69 |     print("TXT文档保存在" + filename)
70 | 
71 | def pdf(url):
72 |     doc_id = re.findall('view/(.*).html',url)[0]
73 |     url = "https://wenku.baidu.com/browse/getbcsurl?doc_id="+doc_id+"&pn=1&rn=99999&type=ppt"
74 |     html = requests.get(url).text
75 |     lists=re.findall('{"zoom":"(.*?)","page"',html)
76 |     for i in range(0,len(lists)):
77 |         lists[i] = lists[i].replace("\\",'')
78 |     try:
79 |         os.mkdir(doc_id)
80 |     except:
81 |         pass
82 |     for i in range(0,len(lists)):
83 |         img=requests.get(lists[i]).content
84 |         with open(doc_id+'\img'+str(i)+'.jpg','wb') as m:
85 |             m.write(img)
86 |     print("PDF图片保存在" + doc_id + "文件夹")
87 | 
88 | def get_type(url):
89 |     data = requests.get(url)
90 |     typee = re.findall("'docType': '(.*?)',",data.text)
91 |     typee_str = typee[0]
92 |     return typee_str
93 | 
94 | 
95 | url = input("URL:")
96 | print("文档类型："+get_type(url))
97 | eval(get_type(url))(url)
98 | print("3秒后退出")
99 | time.sleep(3)


--------------------------------------------------------------------------------