-
Notifications
You must be signed in to change notification settings - Fork 0
/
spider_ikanhm_top.py
219 lines (180 loc) · 8.03 KB
/
spider_ikanhm_top.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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
import os
import shutil
import requests
import time
from bs4 import BeautifulSoup
from urllib.request import urlretrieve
from concurrent.futures import ThreadPoolExecutor
from zhconv import convert
import utils
# 需要额外安装brotli，lxml
class Ikanhm():
def __init__(self):
self.domain = 'http://www.mxshm.top/'
self.headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9',
'cache-control': 'no-cache',
'sec-ch-ua': '"Google Chrome";v="111", "Not(A:Brand";v="8", "Chromium";v="111"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
'sec-fetch-dest': 'empty',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'dnt': '1',
'pragma': 'no-cache',
'referer': self.domain
}
self.proxies={
# 'http':'http://chenkh:[email protected]:10087/',
# 'https':'http://chenkh:[email protected]:10087/',
}
def do_book(self, bookname, book_img_path, stop_num = 5):
print(f"running book with ikanhm: {bookname}")
link = self.get_book_link(bookname)
if link is None:
print(f"bookname {bookname} not found.")
return
chapters = self.get_chapters(link)
if chapters is None or len(chapters) == 0:
print(f"bookname {bookname} get chapters error.")
return
folders=[]
ready_chapters = os.listdir(book_img_path)
no_download_count = 0
for chapter in reversed(chapters):
num = chapter['index']
chapter_name = chapter['name']
chapter_link = chapter['link'].strip()
chapter_name_full = f"{num}. {chapter_name}"
chapter_path = os.path.join(book_img_path, chapter_name_full)
for ready_chapter in ready_chapters:
if chapter_name == ready_chapter[5:]:
if ready_chapter != chapter_name_full:
ready_chapter_path = os.path.join(book_img_path, ready_chapter)
print(f"rename: {ready_chapter_path} -> {chapter_path}")
os.rename(ready_chapter_path, chapter_path)
if not os.path.exists(chapter_path):
os.mkdir(chapter_path)
no_download_count = 0
folders.append(chapter_path)
if stop_num != 0 and no_download_count >= stop_num:
continue
try:
print("load chapter: "+chapter_path)
notdownload = self.get_chapter_pic(chapter_link, chapter_path)
if notdownload:
no_download_count += 1
except Exception as e:
print(e)
all_folders = os.listdir(book_img_path)
for _f in all_folders:
dirpath = os.path.join(book_img_path,_f)
if dirpath not in folders:
print("delete dir: " + dirpath)
shutil.rmtree(dirpath)
def get_book_link(self, bookname):
url = f"{self.domain}/search?keyword={bookname}"
# print(f"request to: {url}")
try:
res = requests.get(url=url, headers=self.headers, proxies=self.proxies)
except Exception as e:
print(e)
return None
res.encoding = 'utf-8'
if res.status_code != 200:
print(f"request to {url} error! code:{res.status_code}")
return None
text = res.text
soup = BeautifulSoup(text, 'lxml')
a_list = soup.select('ul.mh-list > li > div.mh-item > a')
for a_tag in a_list:
link = a_tag.attrs["href"]
title = a_tag.attrs["title"]
if convert(title,'zh-cn') == convert(bookname,'zh-cn'):
return link
return None
def get_chapters(self, link):
url = f"{self.domain}{link}"
# print(f"request to: {url}")
try:
res = requests.get(url=url, headers=self.headers, proxies=self.proxies)
except Exception as e:
print(e)
return []
res.encoding = 'utf-8'
if res.status_code != 200:
print(f"request to {url} error! code:{res.status_code}")
return []
text = res.text
soup = BeautifulSoup(text, 'lxml')
a_list = soup.select('div#chapterlistload > ul#detail-list-select > li > a')
chapters=[]
name_set = []
name_repeats = []
for index, a_tag in enumerate(a_list):
c_name = convert(a_tag.get_text().strip(),'zh-cn')
if c_name in name_set:
name_repeats.append(c_name)
else:
name_set.append(c_name)
chapters.append({
"index":str(index + 1).zfill(3),
"name":c_name,
"link":a_tag.attrs["href"]
})
for name_repeat in name_repeats:
num = 0
for chapter_item in chapters:
if chapter_item["name"] == name_repeat:
num = num + 1
chapter_item["name"] = chapter_item["name"] + str(num)
return chapters
def get_chapter_pic(self, link, chapter_path):
full_url = f'{self.domain}{link}'
# print(f"request to: {full_url}")
res = requests.get(url=full_url, headers=self.headers, proxies=self.proxies)
res.encoding = 'utf-8'
if res.status_code != 200:
print(f"request to {full_url} error! code:{res.status_code}")
return True
text = res.text
soup = BeautifulSoup(text, 'lxml')
img_tags = soup.select('div.comiclist > div.comicpage > div > img')
download_list = []
# need_load = False
for index, img_tag in enumerate(img_tags):
if img_tag.has_attr("data-original"):
img_link = img_tag.attrs["data-original"]
else:
img_link = img_tag.attrs["src"]
img_path = os.path.join(chapter_path, str(index + 1).zfill(3)+".jpg")
if not os.path.exists(img_path):
download_list.append({"img_link": img_link.strip(), "img_path": img_path})
# need_load = True
#if need_load:
if len(download_list) > 0:
pool = ThreadPoolExecutor(max_workers=4)
for download_item in download_list:
pool.submit(utils.download, download_item["img_link"], download_item["img_path"], self.headers, self.proxies)
pool.shutdown()
return False
return True
# if __name__ == '__main__':
# spider = Ikanhm()
# spider.do_book(406,"偷窺（全集无删减）", "/var/www/HanMan/images/偷窺（全集无删减）")
# books = os.listdir('/var/www/HanMan/images')
# for dir in books:
# dir = os.path.join('/var/www/HanMan/images',dir)
# ready_chapters = os.listdir(dir)
# for ready_chapter in ready_chapters:
# # if "&" in ready_chapter:
# # print(f"{dir}/{ready_chapter}")
# a = ready_chapter.replace("…", "…").replace("“", "“").replace("”", "”").replace("♥", "♥")\
# .replace("—", "—").replace("(", "(").replace(")", ")").replace("&", "&").replace("<", "<").replace(">", ">")
# # a = convert(ready_chapter,'zh-cn')#
# if ready_chapter != a:
# print(f"rename: {dir}/{ready_chapter} -> {a}")
# os.rename(os.path.join(dir,ready_chapter), os.path.join(dir,a))