Compare commits
53 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
9c495c4a54 | ||
|
|
51e0467be0 | ||
|
|
59720d8c09 | ||
|
|
150943694b | ||
|
|
f40683e5ec | ||
|
|
912e5ed0fb | ||
|
|
f17994ecf8 | ||
|
|
a414c8eae9 | ||
|
|
8f0eed64c7 | ||
|
|
5f8131f984 | ||
|
|
a574d3a275 | ||
|
|
1813102b0b | ||
|
|
0ef0fed958 | ||
|
|
64be029c78 | ||
|
|
0f77b78133 | ||
|
|
b87f41dc8e | ||
|
|
ecdacdbcb8 | ||
|
|
8308f66ae7 | ||
|
|
44c89590ee | ||
|
|
e7b0980524 | ||
|
|
1cc328bbd7 | ||
|
|
66fbb5efbb | ||
|
|
88fded90ee | ||
|
|
b055f6ca7f | ||
|
|
254e37d9cf | ||
|
|
1c87c26f32 | ||
|
|
10f13f882f | ||
|
|
df17ee59f0 | ||
|
|
07fa18080b | ||
|
|
2bdf2ff283 | ||
|
|
5445f1773c | ||
|
|
b629fb4615 | ||
|
|
d50f5d2f34 | ||
|
|
13f36ddf8b | ||
|
|
295ea2d174 | ||
|
|
ad4fc237b1 | ||
|
|
55d8f02eee | ||
|
|
d6cbd3bdb2 | ||
|
|
99942745c4 | ||
|
|
4daee989e6 | ||
|
|
99b04ef8b5 | ||
|
|
9707f1b38a | ||
|
|
0a9bdd8729 | ||
|
|
8a091a710e | ||
|
|
c5a0ef1f77 | ||
|
|
00b03a4ec4 | ||
|
|
6b4d9ca829 | ||
|
|
ef93ba5eb5 | ||
|
|
46b4557471 | ||
|
|
6b2205887f | ||
|
|
3e0dc60bad | ||
|
|
424ede24eb | ||
|
|
e307ec21e3 |
@@ -2,12 +2,38 @@ import glob
|
||||
import os
|
||||
import time
|
||||
|
||||
#a=glob.glob(os.getcwd()+r"\*.py")
|
||||
a=glob.glob(os.getcwd()+r"\*\**\*.mp4")
|
||||
b=glob.glob(os.getcwd()+r"\*.mp4")
|
||||
for i in b:
|
||||
a.append(i)
|
||||
def movie_lists():
|
||||
#MP4
|
||||
a1 = glob.glob(os.getcwd() + r"\*\**\*.mp4")
|
||||
a2 = glob.glob(os.getcwd() + r"\*.mp4")
|
||||
# AVI
|
||||
b1 = glob.glob(os.getcwd() + r"\*\**\*.avi")
|
||||
b2 = glob.glob(os.getcwd() + r"\*.avi")
|
||||
# RMVB
|
||||
c1 = glob.glob(os.getcwd() + r"\*\**\*.rmvb")
|
||||
c2 = glob.glob(os.getcwd() + r"\*.rmvb")
|
||||
# WMV
|
||||
d1 = glob.glob(os.getcwd() + r"\*\**\*.wmv")
|
||||
d2 = glob.glob(os.getcwd() + r"\*.wmv")
|
||||
# MOV
|
||||
e1 = glob.glob(os.getcwd() + r"\*\**\*.mov")
|
||||
e2 = glob.glob(os.getcwd() + r"\*.mov")
|
||||
# MKV
|
||||
f1 = glob.glob(os.getcwd() + r"\*\**\*.mkv")
|
||||
f2 = glob.glob(os.getcwd() + r"\*.mkv")
|
||||
# FLV
|
||||
g1 = glob.glob(os.getcwd() + r"\*\**\*.flv")
|
||||
g2 = glob.glob(os.getcwd() + r"\*.flv")
|
||||
|
||||
total = a1+a2+b1+b2+c1+c2+d1+d2+e1+e2+f1+f2+g1+g2
|
||||
return total
|
||||
|
||||
def lists_from_test(custom_nuber):
|
||||
a=[]
|
||||
a.append(custom_nuber)
|
||||
return a
|
||||
|
||||
os.chdir(os.getcwd())
|
||||
for i in a:
|
||||
for i in movie_lists():
|
||||
os.system('python core.py'+' "'+i+'"')
|
||||
print("[+]All finished!!!")
|
||||
|
||||
74
README.md
@@ -1,28 +1,66 @@
|
||||
日本AV元数据抓取工具
|
||||
========================
|
||||
**关于本软件**
|
||||
# 日本AV元数据抓取工具 (刮削器)
|
||||
|
||||
## 关于本软件 (~路star谢谢)
|
||||
|
||||
目前,我下的AV越来越多,也意味着AV要集中地管理,形成媒体库。现在有两款主流的AV元数据获取器,"EverAver"和"Javhelper"。前者的优点是元数据获取比较全,缺点是不能批量处理;后者优点是可以批量处理,但是元数据不够全。
|
||||
|
||||
为此,我写出了本软件,为了方便的管理本地AV,和更好的手冲体验。
|
||||
为此,综合上述软件特点,我写出了本软件,为了方便的管理本地AV,和更好的手冲体验。没女朋友怎么办ʅ(‾◡◝)ʃ
|
||||
|
||||
**如何使用**
|
||||
1. 请安装requests,pyquery,lxml,Beautifulsoup,pillow模块,可在CMD逐条输入以下命令安装
|
||||
`pip install requests`
|
||||
`pip install pyquery`
|
||||
`pip install lxml`
|
||||
`pip install beautifulsoup4`
|
||||
`pip install pillow`
|
||||
2. 你的AV在被软件管理前最好命名为番号:**COSQ-004.mp4**
|
||||
文件名中间要有减号"-",没有多余元数据只有番号为最佳,可以让软件更好获取元数据
|
||||
**tg官方电报群:https://t.me/AV_Data_Capture_Official**
|
||||
|
||||

|
||||
### **请认真阅读下面使用说明再使用**
|
||||
|
||||

|
||||
|
||||
|
||||
## 软件流程图 (下下一个为使用教程)
|
||||

|
||||
|
||||
## 如何使用 (使用前请认真阅读下文)
|
||||
**release的程序可脱离python环境运行,可跳过第一步(仅限windows平台)**
|
||||
**下载地址(Windows):https://github.com/wenead99/AV_Data_Capture/releases**
|
||||
1. 请安装requests,pyquery,lxml,Beautifulsoup4,pillow模块,可在CMD逐条输入以下命令安装
|
||||
```python
|
||||
pip install requests
|
||||
```
|
||||
###
|
||||
```python
|
||||
pip install pyquery
|
||||
```
|
||||
###
|
||||
```python
|
||||
pip install lxml
|
||||
```
|
||||
###
|
||||
```python
|
||||
pip install Beautifulsoup4
|
||||
```
|
||||
###
|
||||
```python
|
||||
pip install pillow
|
||||
```
|
||||
|
||||
2. 你的AV在被软件管理前最好命名为番号:
|
||||
```
|
||||
COSQ-004.mp4
|
||||
```
|
||||
文件名中间要有减号"-",没有多余的内容只有番号为最佳,可以让软件更好获取元数据
|
||||
对于多影片重命名,可以用ReNamer来批量重命名
|
||||
软件官网:http://www.den4b.com/products/renamer
|
||||
|
||||

|
||||
|
||||
3. 把软件拷贝到AV的所在目录下,运行程序(中国大陆用户必须挂VPN,Shsadowsocks开全局代理)
|
||||
4. 运行AV_Data_capture.py
|
||||
5. 软件会自动把元数据获取成功的电影移动到JAV_output文件夹中,根据女优分类,失败的电影移动到failed文件夹中。
|
||||
5. **你也可以把单个影片拖动到core程序**
|
||||
|
||||

|
||||
|
||||
6. 软件会自动把元数据获取成功的电影移动到JAV_output文件夹中,根据女优分类,失败的电影移动到failed文件夹中。
|
||||
|
||||

|
||||

|
||||

|
||||
|
||||
|
||||

|
||||

|
||||

|
||||
|
||||
|
||||
38
core.py
@@ -129,33 +129,49 @@ if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("file", help="Write the file path on here")
|
||||
args = parser.parse_args()
|
||||
#===============================
|
||||
#获取文件名称
|
||||
filename=str(os.path.basename(args.file)) #\[\d{4}(\-|\/|.)\d{1,2}\1\d{1,2}\]
|
||||
#去除文件名中日期
|
||||
#print(filename)
|
||||
deldate=str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ","",filename))
|
||||
#print(deldate)
|
||||
number=str(re.search('\w+-\w+',deldate).group())
|
||||
|
||||
#检测是否可以获取番号,如果不行终止本程序
|
||||
def number_getter():
|
||||
print("[!]Making Data for ["+filename+"]")
|
||||
try:
|
||||
a = str(re.search('\w+-\w+', deldate).group())
|
||||
return a
|
||||
except:
|
||||
print('[-]File '+filename+'`s number can not be caught')
|
||||
print('[-]Move ' + filename + 'to failed folder')
|
||||
filepath = str(args).replace("Namespace(file='", '').replace("')", '').replace('\\\\', '\\')
|
||||
if not os.path.exists('failed/'): # 新建failed文件夹
|
||||
os.makedirs('failed/')
|
||||
if not os.path.exists('failed/'):
|
||||
print("[-]failed!Dirs can not be make (Please run as Administrator)")
|
||||
time.sleep(3)
|
||||
os._exit(0)
|
||||
shutil.move(filepath, str(os.getcwd())+'/failed/')
|
||||
os._exit(0)
|
||||
number=number_getter()
|
||||
#print(number)
|
||||
#获取网页信息
|
||||
#获取网页HTML
|
||||
html = get_html("https://www.javbus.com/"+str(number))
|
||||
html_outline=get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid="+number.replace("-",''))
|
||||
#处理超长文件夹名称
|
||||
if len(getActor(html)) > 240:
|
||||
path = 'JAV_output' + '/' + '超多人' + '/' + getNum(html)
|
||||
path = 'JAV_output' + '/' + '超多人' + '/' + getNum(html) #path为影片+元数据所在目录
|
||||
else:
|
||||
path = 'JAV_output' + '/' + getActor(html) + '/' + getNum(html)
|
||||
if not os.path.exists(path):
|
||||
os.makedirs(path)
|
||||
#文件路径处理
|
||||
#print(str(args))
|
||||
filepath = str(args).replace("Namespace(file='",'').replace("')",'').replace('\\\\', '\\')
|
||||
#print(filepath)
|
||||
houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|avi|rmvb|wmv|mov|mp4|mkv|flv)$',filepath).group())
|
||||
print("[!]Making Data for ["+number+houzhui+"]")
|
||||
#下载元数据
|
||||
|
||||
|
||||
if not os.path.exists('failed/'):
|
||||
#如果DownloadFileWithFilename返回为failed,就退出本程序
|
||||
if not os.path.exists('failed/'): #新建failed文件夹
|
||||
os.makedirs('failed/')
|
||||
if not os.path.exists('failed/'):
|
||||
print("[-]failed!Dirs can not be make (Please run as Administrator)")
|
||||
@@ -180,7 +196,7 @@ if __name__ == '__main__':
|
||||
# 电源文件位置处理
|
||||
os.rename(filepath, number + houzhui)
|
||||
shutil.move(number + houzhui, path)
|
||||
#处理元数据
|
||||
#下载元数据
|
||||
PrintFiles(path)
|
||||
print('[!]Finished!')
|
||||
time.sleep(3)
|
||||
1
readme/This is readms.md's images folder
Normal file
@@ -0,0 +1 @@
|
||||
1
|
||||
BIN
readme/flow_chart2.png
Normal file
|
After Width: | Height: | Size: 101 KiB |
|
Before Width: | Height: | Size: 1.1 KiB After Width: | Height: | Size: 1.1 KiB |
|
Before Width: | Height: | Size: 3.4 KiB After Width: | Height: | Size: 3.4 KiB |
|
Before Width: | Height: | Size: 1.3 KiB After Width: | Height: | Size: 1.3 KiB |
|
Before Width: | Height: | Size: 16 KiB After Width: | Height: | Size: 16 KiB |
BIN
readme/readme5.png
Normal file
|
After Width: | Height: | Size: 457 KiB |
BIN
readme/single.gif
Normal file
|
After Width: | Height: | Size: 68 KiB |