├── .gitignore
├── 5tpsMp3
├── 5tpsMp3.py
└── 5tpsMp3_py2.py
├── Ken777
├── Ken777.py
├── Ken777制作书籍汇总.TXT
└── downloaded.txt
├── README.md
├── _test.py
├── doc
└── weiphone.md
├── flvcd.py
├── ifengVideo
└── ifengVideo.py
├── itpub.py
├── lib
├── __init__.py
├── common.py
├── config.ini
└── config.py
├── opencourse.py
├── opencourse_old.py
├── verycd
├── simplecd.py
└── verycd.py
├── weiphone.py
└── youku
└── youku_join.py
/.gitignore:
--------------------------------------------------------------------------------
1 | *.py[co]
2 | __pycache__/
3 |
4 | _test.py
--------------------------------------------------------------------------------
/5tpsMp3/5tpsMp3.py:
--------------------------------------------------------------------------------
1 |
2 | import threading
3 | import signal
4 | import json
5 | import queue
6 |
7 | from lib.common import *
8 |
9 | progress_file = '5tps.json' # 保存进度的文件名
10 | o5tps = {} # 要解析的对象
11 | cur_pos = 0
12 |
13 |
14 | class Parser():
15 | BASE_URL = 'http://www.5tps.com'
16 |
17 | def __init__(self):
18 | # 每个子页面的下载链接、fileName的正则
19 | self.rDownUrl = re.compile(
20 | '点此下载.*')
21 | self.rFileName = re.compile(r'[^/]+\.mp3') # 从上面的DownUrl得到
22 |
23 | #得到 out_dict{'start_url':'', 'title':'', 'urls':[], 'content':'', 'total_size':10}
24 | def parseStartUrl(self, start_url):
25 | """
26 | parse out download page from start url.
27 | eg. we can get 'http://www.5tps.com/down/8297_52_1_1.html' from 'http://www.5tps.com/html/8297.html'
28 | """
29 | out_dict = {'start_url': start_url}
30 | html = getHtml(start_url, 'gbk')
31 |
32 | #标题
33 | titleLine = r1(r'([^<>]*)', html)
34 | title = titleLine.split(" ")[1]
35 | out_dict['title'] = title
36 |
37 | #子链接
38 | rUrl = re.compile(r'href=[\"\'](/down/.*?html)')
39 | itemUrls = rUrl.findall(html)
40 | #/down/8297_52_1_1.html --> http://www.5tps.com/down/8297_52_1_1.html
41 | out_dict['urls'] = [self.BASE_URL + url for url in itemUrls]
42 |
43 | #内容简介
44 | # xpath_contetn = './/*[@id='full']/div/div/ul/p/span' #内容简介
45 | content = re.search(r'