-
Notifications
You must be signed in to change notification settings - Fork 4
/
run.py
159 lines (129 loc) · 4.68 KB
/
run.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
import requests
import time
import os
from bs4 import BeautifulSoup
from os import rename
import filetype
import patoolib
import re
import fileinput
import sys
import argparse
download_url = "http://www.zxcs.me/download.php?id="
book_url = "http://www.zxcs.me/post/"
title_string = ""
author_string = ""
def downloader(url, path):
start = time.time()
size = 0
response = requests.get(url, stream=True)
chunk_size = 1024
content_size = int(response.headers['content-length'])
if response.status_code == 200:
print('[文件名称]:%s' % path)
print('[文件大小]:%0.2f MB' % (content_size / chunk_size / 1024))
with open(path, 'wb') as file:
for data in response.iter_content(chunk_size=chunk_size):
file.write(data)
size += len(data)
print('\r'+'[下载进度]:%s%.2f%%' % ('>'*int(size*50 /
content_size), float(size / content_size * 100)), end='')
end = time.time()
print('\n' + "[下载状态]:%s下载完成！用时%.2f秒" % (path, (end-start)))
print('------------------------------')
def rename_file(path):
file_type = filetype.guess(path)
rename(path, path + '.' + file_type.extension)
def get_one_page(url):
try:
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 Safari/537.36'
}
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.text
return None
except RequestException:
return None
result = input("请输入书籍编号: ")
pic_url = (book_url+result)
dl_url = (download_url+result)
def get_file_name(dl_url):
global title_string
global author_string
html = get_one_page(dl_url)
soup = BeautifulSoup(html, 'lxml')
path = soup.h2.string
title_string = re.search(r'(?<=《)[^》]+',path)[0]
author_string = re.search(r'(?<=作者：).*',path)[0]
return path
filename = (get_file_name(dl_url))
def download_book(dl_url):
global filename
html = get_one_page(dl_url)
soup = BeautifulSoup(html, 'lxml')
path = filename + '.rar'
url = soup.find("a", string="线路一").get("href")
downloader(url=url, path=path)
def download_pic(pic_url):
global filename
html = get_one_page(pic_url)
soup = BeautifulSoup(html, 'lxml')
path = filename + '.jpg'
title = soup.find('title').string.split(" - ")[0]
print(title)
try:
url = soup.find("img", title="点击查看原图").get("src")
except:
url = soup.find("img", alt=title).get("src")
downloader(url=url, path=path)
print("开始下载封面图片.....")
download_pic(pic_url)
print("开始下载书籍压缩文件.....")
download_book(dl_url)
rarname = filename + ".rar"
jpgname = filename + ".jpg"
txtname = filename + ".txt"
epubname = title_string + "-" + author_string + ".epub"
print("正在解压缩文件到当前目录......")
patoolib.extract_archive(rarname, outdir="./")
print("开始文件转码.......")
f = open(txtname, 'r', encoding="gb18030")
content = f.read()
f.close()
f = open(txtname, 'w', encoding="utf-8")
f.write(content)
f.close()
f = open(txtname,'r', encoding="utf-8")
content = f.read()
f.close()
lines = content.split("\n")
new_content = []
new_content.append("% "+ title_string)
new_content.append("% "+ author_string)
for line in lines:
if line == "更多精校小说尽在知轩藏书下载：http://www.zxcs.me/" or line == "==========================================================" or line == title_string or line == title_string + " 作者：" + author_string or line == "作者：" + author_string:
continue
if line == "内容简介：":
new_content.append("# " + line + "\n")
continue
if re.match(r'^\s*[第卷][0123456789一二三四五六七八九十零〇百千两]*[章回部节集卷].*',line):
new_content.append("# " + line + "\n")
continue
line = line.replace(" ","")
new_content.append(line + "\n")
new_content = "\n".join(new_content)
f = open(txtname,'w',encoding="utf=8")
f.write(new_content)
f.close
print("开始转换EPUB文件........")
os.system('pandoc "%s" -o "%s" -t epub3 --css=epub.css --epub-cover-image="%s"' % (txtname, epubname, jpgname))
print("开始转换KEPUB文件.........")
os.system('kepubify -i "%s"' % (epubname))
print("删除残留文件......")
os.system("rm '%s'" % (txtname))
os.system("rm '%s'" % (jpgname))
os.system("rm '%s'" % (rarname))
os.system("mv *.kepub.epub ./kepub/")
os.system("mv *.epub ./epub/")
print("完成，收工，撒花！！🎉🎉")