Compare commits
20 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
f99def64bb | ||
|
|
94c4838b42 | ||
|
|
73c0126fb8 | ||
|
|
ae99c652f5 | ||
|
|
2b9ce63601 | ||
|
|
6928df8c3f | ||
|
|
8ccdf7dc5a | ||
|
|
b438312c97 | ||
|
|
fd05706636 | ||
|
|
1e407ef962 | ||
|
|
9898932f09 | ||
|
|
c4fc22054b | ||
|
|
449e900837 | ||
|
|
e3ebbec947 | ||
|
|
65a9521ab1 | ||
|
|
b79a600c0d | ||
|
|
30d33fe8f7 | ||
|
|
b325fc1f01 | ||
|
|
954fb02c0c | ||
|
|
5ee398d6b5 |
@@ -1,3 +1,4 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import requests
|
||||
@@ -18,17 +19,13 @@ if os.path.exists(config_file):
|
||||
else:
|
||||
print('[+]config.ini: not found, creating...')
|
||||
with open("config.ini", "wt", encoding='UTF-8') as code:
|
||||
print("[common]", file=code)
|
||||
print("failed_output_folder=failed", file=code)
|
||||
print("success_output_folder=JAV_output", file=code)
|
||||
print("", file=code)
|
||||
print("[proxy]",file=code)
|
||||
print("proxy=127.0.0.1:1080",file=code)
|
||||
print("timeout=10", file=code)
|
||||
print("retry=3", file=code)
|
||||
print("", file=code)
|
||||
print("[Name_Rule]", file=code)
|
||||
print("location_rule=actor+'/'+number",file=code)
|
||||
print("location_rule='JAV_output/'+actor+'/'+number",file=code)
|
||||
print("naming_rule=number+'-'+title",file=code)
|
||||
print("", file=code)
|
||||
print("[update]",file=code)
|
||||
@@ -40,8 +37,10 @@ else:
|
||||
print("#plex only test!", file=code)
|
||||
print("", file=code)
|
||||
print("[directory_capture]", file=code)
|
||||
print("switch=0", file=code)
|
||||
print("directory=", file=code)
|
||||
print("", file=code)
|
||||
print("everyone switch:1=on, 0=off", file=code)
|
||||
time.sleep(2)
|
||||
print('[+]config.ini: created!')
|
||||
try:
|
||||
|
||||
@@ -14,7 +14,7 @@ os.chdir(os.getcwd())
|
||||
|
||||
# ============global var===========
|
||||
|
||||
version='0.11.9'
|
||||
version='1.3'
|
||||
|
||||
config = ConfigParser()
|
||||
config.read(config_file, encoding='UTF-8')
|
||||
@@ -25,47 +25,37 @@ Platform = sys.platform
|
||||
|
||||
def UpdateCheck():
|
||||
if UpdateCheckSwitch() == '1':
|
||||
html2 = get_html('https://raw.githubusercontent.com/wenead99/AV_Data_Capture/master/update_check.json')
|
||||
html2 = get_html('https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/update_check.json')
|
||||
html = json.loads(str(html2))
|
||||
|
||||
if not version == html['version']:
|
||||
print('[*] * New update ' + html['version'] + ' *')
|
||||
print('[*] * New update ' + html['version'] + ' *')
|
||||
print('[*] * Download *')
|
||||
print('[*] ' + html['download'])
|
||||
print('[*]=====================================')
|
||||
else:
|
||||
print('[+]Update Check disabled!')
|
||||
def movie_lists():
|
||||
global exclude_directory_1
|
||||
global exclude_directory_2
|
||||
directory = config['directory_capture']['directory']
|
||||
a2=[]
|
||||
b2=[]
|
||||
c2=[]
|
||||
d2=[]
|
||||
e2=[]
|
||||
f2=[]
|
||||
g2=[]
|
||||
h2=[]
|
||||
total=[]
|
||||
file_type = ['mp4','avi','rmvb','wmv','mov','mkv','flv','ts']
|
||||
exclude_directory_1 = config['common']['failed_output_folder']
|
||||
exclude_directory_2 = config['common']['success_output_folder']
|
||||
if directory=='*':
|
||||
remove_total = []
|
||||
for o in file_type:
|
||||
remove_total += glob.glob(r"./" + exclude_directory_1 + "/*." + o)
|
||||
remove_total += glob.glob(r"./" + exclude_directory_2 + "/*." + o)
|
||||
for i in os.listdir(os.getcwd()):
|
||||
a2 += glob.glob(r"./" + i + "/*.mp4")
|
||||
b2 += glob.glob(r"./" + i + "/*.avi")
|
||||
c2 += glob.glob(r"./" + i + "/*.rmvb")
|
||||
d2 += glob.glob(r"./" + i + "/*.wmv")
|
||||
e2 += glob.glob(r"./" + i + "/*.mov")
|
||||
f2 += glob.glob(r"./" + i + "/*.mkv")
|
||||
g2 += glob.glob(r"./" + i + "/*.flv")
|
||||
h2 += glob.glob(r"./" + i + "/*.ts")
|
||||
total = a2 + b2 + c2 + d2 + e2 + f2 + g2 + h2
|
||||
for a in file_type:
|
||||
total += glob.glob(r"./" + i + "/*." + a)
|
||||
for b in remove_total:
|
||||
total.remove(b)
|
||||
return total
|
||||
a2 = glob.glob(r"./" + directory + "/*.mp4")
|
||||
b2 = glob.glob(r"./" + directory + "/*.avi")
|
||||
c2 = glob.glob(r"./" + directory + "/*.rmvb")
|
||||
d2 = glob.glob(r"./" + directory + "/*.wmv")
|
||||
e2 = glob.glob(r"./" + directory + "/*.mov")
|
||||
f2 = glob.glob(r"./" + directory + "/*.mkv")
|
||||
g2 = glob.glob(r"./" + directory + "/*.flv")
|
||||
h2 = glob.glob(r"./" + directory + "/*.ts")
|
||||
total = a2 + b2 + c2 + d2 + e2 + f2 + g2 + h2
|
||||
for a in file_type:
|
||||
total += glob.glob(r"./" + directory + "/*." + a)
|
||||
return total
|
||||
def CreatFailedFolder():
|
||||
if not os.path.exists('failed/'): # 新建failed文件夹
|
||||
@@ -79,13 +69,13 @@ def lists_from_test(custom_nuber): #电影列表
|
||||
a.append(custom_nuber)
|
||||
return a
|
||||
def CEF(path):
|
||||
files = os.listdir(path) # 获取路径下的子文件(夹)列表
|
||||
for file in files:
|
||||
try: #试图删除空目录,非空目录删除会报错
|
||||
try:
|
||||
files = os.listdir(path) # 获取路径下的子文件(夹)列表
|
||||
for file in files:
|
||||
os.removedirs(path + '/' + file) # 删除这个空文件夹
|
||||
print('[+]Deleting empty folder',path + '/' + file)
|
||||
except:
|
||||
a=''
|
||||
print('[+]Deleting empty folder', path + '/' + file)
|
||||
except:
|
||||
a=''
|
||||
def rreplace(self, old, new, *max):
|
||||
#从右开始替换文件名中内容，源字符串，将被替换的子字符串， 新字符串，用于替换old子字符串，可选字符串, 替换不超过 max 次
|
||||
count = len(self)
|
||||
@@ -93,32 +83,28 @@ def rreplace(self, old, new, *max):
|
||||
count = max[0]
|
||||
return new.join(self.rsplit(old, count))
|
||||
def getNumber(filepath):
|
||||
filepath = filepath.replace('.\\','')
|
||||
try: # 普通提取番号 主要处理包含减号-的番号
|
||||
filepath1 = filepath.replace("_", "-")
|
||||
filepath1.strip('22-sht.me').strip('-HD').strip('-hd')
|
||||
filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath1)) # 去除文件名中时间
|
||||
file_number = re.search('\w+-\d+', filename).group()
|
||||
filepath = filepath.replace("_", "-")
|
||||
filepath.strip('22-sht.me').strip('-HD').strip('-hd')
|
||||
filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath)) # 去除文件名中时间
|
||||
try:
|
||||
file_number = re.search('\w+-\d+', filename).group()
|
||||
except: # 提取类似mkbd-s120番号
|
||||
file_number = re.search('\w+-\w+\d+', filename).group()
|
||||
return file_number
|
||||
except: # 提取不含减号-的番号
|
||||
try: # 提取东京热番号格式 n1087
|
||||
filename1 = str(re.sub("h26\d", "", filepath)).strip('Tokyo-hot').strip('tokyo-hot')
|
||||
filename0 = str(re.sub(".*?\.com-\d+", "", filename1)).strip('_')
|
||||
if '-C.' in filepath or '-c.' in filepath:
|
||||
cn_sub = '1'
|
||||
file_number = str(re.search('n\d{4}', filename0).group(0))
|
||||
try:
|
||||
filename = str(re.sub("ts6\d", "", filepath)).strip('Tokyo-hot').strip('tokyo-hot')
|
||||
filename = str(re.sub(".*?\.com-\d+", "", filename)).replace('_', '')
|
||||
file_number = str(re.search('\w+\d{4}', filename).group(0))
|
||||
return file_number
|
||||
except: # 提取无减号番号
|
||||
filename1 = str(re.sub("h26\d", "", filepath)) # 去除h264/265
|
||||
filename0 = str(re.sub(".*?\.com-\d+", "", filename1))
|
||||
file_number2 = str(re.match('\w+', filename0).group())
|
||||
if '-C.' in filepath or '-c.' in filepath:
|
||||
cn_sub = '1'
|
||||
file_number = str(file_number2.replace(re.match("^[A-Za-z]+", file_number2).group(),
|
||||
re.match("^[A-Za-z]+", file_number2).group() + '-'))
|
||||
filename = str(re.sub("ts6\d", "", filepath)) # 去除ts64/265
|
||||
filename = str(re.sub(".*?\.com-\d+", "", filename))
|
||||
file_number = str(re.match('\w+', filename).group())
|
||||
file_number = str(file_number.replace(re.match("^[A-Za-z]+", file_number).group(),re.match("^[A-Za-z]+", file_number).group() + '-'))
|
||||
return file_number
|
||||
# if not re.search('\w-', file_number).group() == 'None':
|
||||
# file_number = re.search('\w+-\w+', filename).group()
|
||||
#
|
||||
|
||||
def RunCore():
|
||||
if Platform == 'win32':
|
||||
@@ -138,7 +124,7 @@ def RunCore():
|
||||
|
||||
if __name__ =='__main__':
|
||||
print('[*]===========AV Data Capture===========')
|
||||
print('[*] Version '+version)
|
||||
print('[*] Version '+version)
|
||||
print('[*]=====================================')
|
||||
CreatFailedFolder()
|
||||
UpdateCheck()
|
||||
@@ -161,7 +147,7 @@ if __name__ =='__main__':
|
||||
shutil.move(i, str(os.getcwd()) + '/' + 'failed/')
|
||||
continue
|
||||
|
||||
|
||||
CEF('JAV_output')
|
||||
CEF(exclude_directory_1)
|
||||
CEF(exclude_directory_2)
|
||||
print("[+]All finished!!!")
|
||||
input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看和错误信息。")
|
||||
68
README.md
68
README.md
@@ -5,7 +5,8 @@
|
||||
|
||||
<br>
|
||||
|
||||
<br>
|
||||
|
||||
<br>
|
||||
|
||||
|
||||
**日本电影元数据 抓取工具 | 刮削器**，配合本地影片管理软件EMBY,KODI管理本地影片，该软件起到分类与元数据抓取作用，利用元数据信息来分类，供本地影片分类整理使用。
|
||||
@@ -25,13 +26,15 @@
|
||||
* [影片原路径处理](#4建议把软件拷贝和电影的统一目录下)
|
||||
* [异常处理（重要）](#51异常处理重要)
|
||||
* [导入至媒体库](#7把jav_output文件夹导入到embykodi中等待元数据刷新完成)
|
||||
* [写在后面](#8写在后面)
|
||||
* [关于群晖NAS](#8关于群晖NAS)
|
||||
* [写在后面](#9写在后面)
|
||||
|
||||
# 免责声明
|
||||
1.本软件仅供**技术交流，学术交流**使用，本项目旨在学习 Python3<br>
|
||||
2.本软件禁止用于任何非法用途<br>
|
||||
3.使用者使用该软件产生的一切法律后果由使用者承担<br>
|
||||
4.不可使用于商业和个人其他意图<br>
|
||||
* 本软件仅供**技术交流，学术交流**使用，本项目旨在学习 Python3<br>
|
||||
* 本软件禁止用于任何非法用途<br>
|
||||
* 使用者使用该软件产生的一切法律后果由使用者承担<br>
|
||||
* 不可使用于商业和个人其他意图<br>
|
||||
* 使用该软件前，请自觉遵守当地法律法规
|
||||
|
||||
# 注意
|
||||
**推荐用法: 使用该软件后，对于不能正常获取元数据的电影可以用 Everaver 来补救**<br>
|
||||
@@ -54,7 +57,7 @@
|
||||
|
||||
# 如何使用
|
||||
### 下载
|
||||
* release的程序可脱离**python环境**运行，可跳过 [模块安装](#1请安装模块在cmd终端逐条输入以下命令安装)<br>Release 下载地址(**仅限Windows**):<br>[](https://github.com/yoshiko2/AV_Data_Capture/releases/download/0.11.6/Beta11.6.zip)<br>
|
||||
* release的程序可脱离**python环境**运行，可跳过 [模块安装](#1请安装模块在cmd终端逐条输入以下命令安装)<br>Release 下载地址(**仅限Windows**):<br>[](https://github.com/yoshiko2/AV_Data_Capture/releases)<br>
|
||||
* Linux,MacOS请下载源码包运行
|
||||
|
||||
* Windows Python环境:[点击前往](https://www.python.org/downloads/windows/) 选中executable installer下载
|
||||
@@ -112,6 +115,7 @@ config.ini
|
||||
>directory=<br>
|
||||
|
||||
### 全局设置
|
||||
---
|
||||
#### 软件模式
|
||||
>[common]<br>
|
||||
>main_mode=1<br>
|
||||
@@ -123,6 +127,7 @@ config.ini
|
||||
|
||||
设置成功输出目录和失败输出目录
|
||||
|
||||
---
|
||||
### 网络设置
|
||||
#### * 针对“某些地区”的代理设置
|
||||
打开```config.ini```,在```[proxy]```下的```proxy```行设置本地代理地址和端口，支持Shadowxxxx/X,V2XXX本地代理端口:<br>
|
||||
@@ -135,18 +140,22 @@ config.ini
|
||||
>timeout=10<br>
|
||||
|
||||
10为超时重试时间 单位：秒
|
||||
|
||||
---
|
||||
#### 连接重试次数设置
|
||||
>[proxy]<br>
|
||||
>retry=3<br>
|
||||
|
||||
3即为重试次数
|
||||
|
||||
---
|
||||
#### 检查更新开关
|
||||
>[update]<br>
|
||||
>update_check=1<br>
|
||||
|
||||
0为关闭，1为开启，不建议关闭
|
||||
|
||||
---
|
||||
##### 媒体库选择
|
||||
>[media]<br>
|
||||
>media_warehouse=emby<br>
|
||||
@@ -155,18 +164,26 @@ config.ini
|
||||
可选择emby, plex<br>
|
||||
如果是PLEX，请安装插件：```XBMCnfoMoviesImporter```
|
||||
|
||||
---
|
||||
#### 调试模式
|
||||
>[debug_mode]<br>switch=1<br>
|
||||
|
||||
如要开启调试模式，请手动输入以上代码到```config.ini```中，开启后可在抓取中显示影片元数据
|
||||
|
||||
---
|
||||
#### 抓取目录选择
|
||||
>[directory_capture]<br>
|
||||
>directory=<br>
|
||||
如果directory后面为空，则抓取和程序同一目录下的影片，设置为``` * ```可抓取软件所在目录下的所有子目录中的影片
|
||||
|
||||
## 3.(可选)设置自定义目录和影片重命名规则
|
||||
### 3.(可选)设置自定义目录和影片重命名规则
|
||||
>[Name_Rule]<br>
|
||||
>location_rule=actor+'/'+number<br>
|
||||
>naming_rule=number+'-'+title<br>
|
||||
|
||||
**已有默认配置**<br>
|
||||
#### 命名参数<br>
|
||||
已有默认配置
|
||||
|
||||
---
|
||||
#### 命名参数
|
||||
>title = 片名<br>
|
||||
>actor = 演员<br>
|
||||
>studio = 公司<br>
|
||||
@@ -178,12 +195,18 @@ config.ini
|
||||
>tag = 类型<br>
|
||||
>outline = 简介<br>
|
||||
>runtime = 时长<br>
|
||||
##### **例子**:<br>
|
||||
目录结构规则:```location_rule=actor+'/'+number```<br> **不推荐修改时在这里添加title**，有时title过长，因为Windows API问题，抓取数据时新建文件夹容易出错。<br>
|
||||
影片命名规则:```naming_rule=number+'-'+title```<br> **在EMBY,KODI等本地媒体库显示的标题，不影响目录结构下影片文件的命名**，依旧是 番号+后缀。
|
||||
|
||||
上面的参数以下都称之为**变量**
|
||||
|
||||
#### 例子：
|
||||
自定义规则方法：有两种元素，变量和字符，无论是任何一种元素之间连接必须要用加号 **+** ，比如：```'naming_rule=['+number+']-'+title```，其中冒号 ' ' 内的文字是字符，没有冒号包含的文字是变量，元素之间连接必须要用加号 **+** <br>
|
||||
目录结构规则：默认 ```location_rule=actor+'/'+number```<br> **不推荐修改时在这里添加title**，有时title过长，因为Windows API问题，抓取数据时新建文件夹容易出错。<br>
|
||||
影片命名规则：默认 ```naming_rule=number+'-'+title```<br> **在EMBY,KODI等本地媒体库显示的标题，不影响目录结构下影片文件的命名**，依旧是 番号+后缀。
|
||||
|
||||
### 更新开关
|
||||
>[update]<br>update_check=1<br>
|
||||
1为开，0为关
|
||||
|
||||
## 4.建议把软件拷贝和电影的统一目录下
|
||||
如果```config.ini```中```directory=```后面为空的情况下
|
||||
## 5.运行 ```AV_Data_capture.py/.exe```
|
||||
@@ -191,16 +214,27 @@ config.ini
|
||||
中文，字幕，-c., -C., 处理元数据时会加上**中文字幕**标签
|
||||
## 5.1 异常处理（重要）
|
||||
### 请确保软件是完整地！确保ini文件内容是和下载提供ini文件内容的一致的！
|
||||
---
|
||||
### 关于软件打开就闪退
|
||||
可以打开cmd命令提示符，把 ```AV_Data_capture.py/.exe```拖进cmd窗口回车运行，查看错误，出现的错误信息**依据以下条目解决**
|
||||
|
||||
---
|
||||
### 关于 ```Updata_check``` 和 ```JSON``` 相关的错误
|
||||
跳转 [网络设置](#网络设置)
|
||||
|
||||
---
|
||||
### 关于```FileNotFoundError: [WinError 3] 系统找不到指定的路径。: 'JAV_output''```
|
||||
在软件所在文件夹下新建 JAV_output 文件夹，可能是你没有把软件拉到和电影的同一目录
|
||||
|
||||
---
|
||||
### 关于连接拒绝的错误
|
||||
请设置好[代理](#针对某些地区的代理设置)<br>
|
||||
|
||||
---
|
||||
### 关于Nonetype,xpath报错
|
||||
同上<br>
|
||||
|
||||
---
|
||||
### 关于番号提取失败或者异常
|
||||
**目前可以提取元素的影片:JAVBUS上有元数据的电影，素人系列:300Maan,259luxu,siro等,FC2系列**<br>
|
||||
>下一张图片来自Pockies的blog 原作者已授权<br>
|
||||
@@ -217,13 +251,17 @@ COSQ-004.mp4
|
||||
**野鸡番号**:比如 ```XXX-XXX-1```, ```1301XX-MINA_YUKA``` 这种**野鸡**番号，在javbus等资料库存在的作品。<br>**重要**：除了 **影片文件名** ```XXXX-XXX-C```，后面这种-C的是指电影有中文字幕！<br>
|
||||
条件：文件名中间要有下划线或者减号"_","-"，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](http://www.den4b.com/products/renamer)来批量重命名<br>
|
||||
|
||||
---
|
||||
### 关于PIL/image.py
|
||||
暂时无解，可能是网络问题或者pillow模块打包问题，你可以用源码运行（要安装好第一步的模块）
|
||||
|
||||
|
||||
## 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，根据演员分类，失败的电影移动到failed文件夹中。
|
||||
## 7.把JAV_output文件夹导入到EMBY,KODI中，等待元数据刷新，完成
|
||||
## 8.写在后面
|
||||
## 8.关于群晖NAS
|
||||
开启SMB在Windows上挂载为网络磁盘即可使用本软件，也适用于其他NAS
|
||||
## 9.写在后面
|
||||
怎么样，看着自己的日本电影被这样完美地管理，是不是感觉成就感爆棚呢?<br>
|
||||
**tg官方电报群:[ 点击进群](https://t.me/AV_Data_Capture_Official)**<br>
|
||||
|
||||
|
||||
112
avsox.py
Normal file
112
avsox.py
Normal file
@@ -0,0 +1,112 @@
|
||||
import re
|
||||
from lxml import etree
|
||||
import json
|
||||
from bs4 import BeautifulSoup
|
||||
from ADC_function import *
|
||||
|
||||
def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'avatar-box'})
|
||||
d = {}
|
||||
for i in a:
|
||||
l = i.img['src']
|
||||
t = i.span.get_text()
|
||||
p2 = {t: l}
|
||||
d.update(p2)
|
||||
return d
|
||||
def getTitle(a):
|
||||
try:
|
||||
html = etree.fromstring(a, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/h3/text()')).strip(" ['']") #[0]
|
||||
return result.replace('/', '')
|
||||
except:
|
||||
return ''
|
||||
def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
|
||||
soup = BeautifulSoup(a, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'avatar-box'})
|
||||
d = []
|
||||
for i in a:
|
||||
d.append(i.span.get_text())
|
||||
return d
|
||||
def getStudio(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//p[contains(text(),"制作商: ")]/following-sibling::p[1]/a/text()')).strip(" ['']").replace("', '",' ')
|
||||
return result1
|
||||
def getRuntime(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//span[contains(text(),"长度:")]/../text()')).strip(" ['分钟']")
|
||||
return result1
|
||||
def getLabel(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//p[contains(text(),"系列:")]/following-sibling::p[1]/a/text()')).strip(" ['']")
|
||||
return result1
|
||||
def getNum(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//span[contains(text(),"识别码:")]/../span[2]/text()')).strip(" ['']")
|
||||
return result1
|
||||
def getYear(release):
|
||||
try:
|
||||
result = str(re.search('\d{4}',release).group())
|
||||
return result
|
||||
except:
|
||||
return release
|
||||
def getRelease(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//span[contains(text(),"发行时间:")]/../text()')).strip(" ['']")
|
||||
return result1
|
||||
def getCover(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div[1]/div[1]/a/img/@src')).strip(" ['']")
|
||||
return result
|
||||
def getCover_small(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="waterfall"]/div/a/div[1]/img/@src')).strip(" ['']")
|
||||
return result
|
||||
def getTag(a): # 获取演员
|
||||
soup = BeautifulSoup(a, 'lxml')
|
||||
a = soup.find_all(attrs={'class': 'genre'})
|
||||
d = []
|
||||
for i in a:
|
||||
d.append(i.get_text())
|
||||
return d
|
||||
|
||||
def main(number):
|
||||
a = get_html('https://avsox.asia/cn/search/' + number)
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
|
||||
if result1 == '' or result1 == 'null' or result1 == 'None':
|
||||
a = get_html('https://avsox.asia/cn/search/' + number.replace('-', '_'))
|
||||
print(a)
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
|
||||
if result1 == '' or result1 == 'null' or result1 == 'None':
|
||||
a = get_html('https://avsox.asia/cn/search/' + number.replace('_', ''))
|
||||
print(a)
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
|
||||
web = get_html(result1)
|
||||
soup = BeautifulSoup(web, 'lxml')
|
||||
info = str(soup.find(attrs={'class': 'row movie'}))
|
||||
dic = {
|
||||
'actor': getActor(web),
|
||||
'title': getTitle(web).strip(getNum(web)),
|
||||
'studio': getStudio(info),
|
||||
'outline': '',#
|
||||
'runtime': getRuntime(info),
|
||||
'director': '', #
|
||||
'release': getRelease(info),
|
||||
'number': getNum(info),
|
||||
'cover': getCover(web),
|
||||
'cover_small': getCover_small(a),
|
||||
'imagecut': 3,
|
||||
'tag': getTag(web),
|
||||
'label': getLabel(info),
|
||||
'year': getYear(getRelease(info)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': getActorPhoto(web),
|
||||
'website': result1,
|
||||
'source': 'avsox.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
|
||||
#print(main('041516_541'))
|
||||
11
config.ini
11
config.ini
@@ -1,10 +1,15 @@
|
||||
[common]
|
||||
main_mode=1
|
||||
failed_output_folder=failed
|
||||
success_output_folder=JAV_output
|
||||
|
||||
[proxy]
|
||||
proxy=127.0.0.1:1080
|
||||
timeout=10
|
||||
retry=3
|
||||
|
||||
[Name_Rule]
|
||||
location_rule='JAV_output/'+actor+'/'+number
|
||||
location_rule=actor+'/'+number
|
||||
naming_rule=number+'-'+title
|
||||
|
||||
[update]
|
||||
@@ -13,10 +18,6 @@ update_check=1
|
||||
[media]
|
||||
media_warehouse=emby
|
||||
#emby or plex
|
||||
#plex only test!
|
||||
|
||||
[directory_capture]
|
||||
switch=0
|
||||
directory=
|
||||
|
||||
#everyone switch:1=on, 0=off
|
||||
210
core.py
210
core.py
@@ -6,23 +6,25 @@ import os.path
|
||||
import shutil
|
||||
from PIL import Image
|
||||
import time
|
||||
import javbus
|
||||
import json
|
||||
import fc2fans_club
|
||||
import siro
|
||||
from ADC_function import *
|
||||
from configparser import ConfigParser
|
||||
import argparse
|
||||
#=========website========
|
||||
import fc2fans_club
|
||||
import siro
|
||||
import avsox
|
||||
import javbus
|
||||
import javdb
|
||||
#=========website========
|
||||
|
||||
#初始化全局变量
|
||||
Config = ConfigParser()
|
||||
Config.read(config_file, encoding='UTF-8')
|
||||
try:
|
||||
option = ReadMediaWarehouse()
|
||||
except:
|
||||
print('[-]Config media_warehouse read failed!')
|
||||
|
||||
#初始化全局变量
|
||||
title=''
|
||||
studio=''
|
||||
year=''
|
||||
@@ -37,17 +39,21 @@ cover=''
|
||||
imagecut=''
|
||||
tag=[]
|
||||
cn_sub=''
|
||||
multi_part=0
|
||||
part=''
|
||||
path=''
|
||||
houzhui=''
|
||||
website=''
|
||||
json_data={}
|
||||
actor_photo={}
|
||||
cover_small=''
|
||||
naming_rule =''#eval(config['Name_Rule']['naming_rule'])
|
||||
location_rule=''#eval(config['Name_Rule']['location_rule'])
|
||||
program_mode = Config['common']['main_mode']
|
||||
failed_folder= Config['common']['failed_output_folder']
|
||||
success_folder=Config['common']['success_output_folder']
|
||||
program_mode = Config['common']['main_mode']
|
||||
failed_folder = Config['common']['failed_output_folder']
|
||||
success_folder = Config['common']['success_output_folder']
|
||||
#=====================本地文件处理===========================
|
||||
|
||||
def moveFailedFolder():
|
||||
global filepath
|
||||
print('[-]Move to Failed output folder')
|
||||
@@ -66,6 +72,11 @@ def CreatFailedFolder():
|
||||
except:
|
||||
print("[-]failed!can not be make Failed output folder\n[-](Please run as Administrator)")
|
||||
os._exit(0)
|
||||
def getDataState(json_data): #元数据获取失败检测
|
||||
if json_data['title'] == '' or json_data['title'] == 'None' or json_data['title'] == 'null':
|
||||
return 0
|
||||
else:
|
||||
return 1
|
||||
def getDataFromJSON(file_number): #从JSON返回元数据
|
||||
global title
|
||||
global studio
|
||||
@@ -84,29 +95,41 @@ def getDataFromJSON(file_number): #从JSON返回元数据
|
||||
global cn_sub
|
||||
global website
|
||||
global actor_photo
|
||||
global cover_small
|
||||
global json_data
|
||||
|
||||
global naming_rule
|
||||
global location_rule
|
||||
|
||||
|
||||
# ================================================网站规则添加开始================================================
|
||||
|
||||
try: # 添加 需要 正则表达式的规则
|
||||
# =======================javdb.py=======================
|
||||
if re.search('^\d{5,}', file_number).group() in file_number:
|
||||
json_data = json.loads(javbus.main_uncensored(file_number))
|
||||
except: # 添加 无需 正则表达式的规则
|
||||
# ====================fc2fans_club.py====================
|
||||
if 'fc2' in file_number:
|
||||
json_data = json.loads(fc2fans_club.main(file_number.strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-').strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-')))
|
||||
elif 'FC2' in file_number:
|
||||
json_data = json.loads(fc2fans_club.main(file_number.strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-').strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-')))
|
||||
# =======================siro.py=========================
|
||||
elif 'siro' in file_number or 'SIRO' in file_number or 'Siro' in file_number:
|
||||
json_data = json.loads(siro.main(file_number))
|
||||
# =======================javbus.py=======================
|
||||
else:
|
||||
if re.match('^\d{5,}', file_number):
|
||||
json_data = json.loads(avsox.main(file_number))
|
||||
if getDataState(json_data) == 0: # 如果元数据获取失败，请求番号至其他网站抓取
|
||||
json_data = json.loads(javdb.main(file_number))
|
||||
#==
|
||||
elif re.match('\d+\D+', file_number):
|
||||
json_data = json.loads(siro.main(file_number))
|
||||
if getDataState(json_data) == 0: # 如果元数据获取失败，请求番号至其他网站抓取
|
||||
json_data = json.loads(javbus.main(file_number))
|
||||
elif getDataState(json_data) == 0: # 如果元数据获取失败，请求番号至其他网站抓取
|
||||
json_data = json.loads(javdb.main(file_number))
|
||||
# ==
|
||||
elif 'fc2' in file_number or 'FC2' in file_number:
|
||||
json_data = json.loads(fc2fans_club.main(file_number))
|
||||
# ==
|
||||
elif 'HEYZO' in number or 'heyzo' in number or 'Heyzo' in number:
|
||||
json_data = json.loads(avsox.main(file_number))
|
||||
# ==
|
||||
elif 'siro' in file_number or 'SIRO' in file_number or 'Siro' in file_number:
|
||||
json_data = json.loads(siro.main(file_number))
|
||||
# ==
|
||||
else:
|
||||
json_data = json.loads(javbus.main(file_number))
|
||||
if getDataState(json_data) == 0: # 如果元数据获取失败，请求番号至其他网站抓取
|
||||
json_data = json.loads(avsox.main(file_number))
|
||||
elif getDataState(json_data) == 0: # 如果元数据获取失败，请求番号至其他网站抓取
|
||||
json_data = json.loads(javdb.main(file_number))
|
||||
|
||||
# ================================================网站规则添加结束================================================
|
||||
|
||||
@@ -120,45 +143,61 @@ def getDataFromJSON(file_number): #从JSON返回元数据
|
||||
release = json_data['release']
|
||||
number = json_data['number']
|
||||
cover = json_data['cover']
|
||||
try:
|
||||
cover_small = json_data['cover_small']
|
||||
except:
|
||||
cover_small=''
|
||||
imagecut = json_data['imagecut']
|
||||
tag = str(json_data['tag']).strip("[ ]").replace("'", '').replace(" ", '').split(',') # 字符串转列表
|
||||
tag = str(json_data['tag']).strip("[ ]").replace("'", '').replace(" ", '').split(',') # 字符串转列表 @
|
||||
actor = str(actor_list).strip("[ ]").replace("'", '').replace(" ", '')
|
||||
actor_photo = json_data['actor_photo']
|
||||
website = json_data['website']
|
||||
source = json_data['source']
|
||||
|
||||
if title == '' or number == '':
|
||||
print('[-]Movie Data not found!')
|
||||
moveFailedFolder()
|
||||
|
||||
if imagecut == '3':
|
||||
DownloadFileWithFilename()
|
||||
|
||||
|
||||
# ====================处理异常字符====================== #\/:*?"<>|
|
||||
if '\\' in title:
|
||||
title=title.replace('\\', ' ')
|
||||
elif r'/' in title:
|
||||
title=title.replace(r'/', '')
|
||||
elif ':' in title:
|
||||
title=title.replace(':', '')
|
||||
elif '*' in title:
|
||||
title=title.replace('*', '')
|
||||
elif '?' in title:
|
||||
title=title.replace('?', '')
|
||||
elif '"' in title:
|
||||
title=title.replace('"', '')
|
||||
elif '<' in title:
|
||||
title=title.replace('<', '')
|
||||
elif '>' in title:
|
||||
title=title.replace('>', '')
|
||||
elif '|' in title:
|
||||
title=title.replace('|', '')
|
||||
title = title.replace('\\', '')
|
||||
title = title.replace('/', '')
|
||||
title = title.replace(':', '')
|
||||
title = title.replace('*', '')
|
||||
title = title.replace('?', '')
|
||||
title = title.replace('"', '')
|
||||
title = title.replace('<', '')
|
||||
title = title.replace('>', '')
|
||||
title = title.replace('|', '')
|
||||
# ====================处理异常字符 END================== #\/:*?"<>|
|
||||
|
||||
naming_rule = eval(config['Name_Rule']['naming_rule'])
|
||||
location_rule = eval(config['Name_Rule']['location_rule'])
|
||||
def smallCoverCheck():
|
||||
if imagecut == 3:
|
||||
if option == 'emby':
|
||||
DownloadFileWithFilename(cover_small, '1.jpg', path)
|
||||
img = Image.open(path + '/1.jpg')
|
||||
w = img.width
|
||||
h = img.height
|
||||
img.save(path + '/' + number + '.png')
|
||||
time.sleep(1)
|
||||
os.remove(path + '/1.jpg')
|
||||
if option == 'plex':
|
||||
DownloadFileWithFilename(cover_small, '1.jpg', path)
|
||||
img = Image.open(path + '/1.jpg')
|
||||
w = img.width
|
||||
h = img.height
|
||||
img.save(path + '/poster.png')
|
||||
os.remove(path + '/1.jpg')
|
||||
def creatFolder(): #创建文件夹
|
||||
global actor
|
||||
global path
|
||||
if len(actor) > 240: #新建成功输出文件夹
|
||||
if len(os.getcwd()+path) > 240: #新建成功输出文件夹
|
||||
path = success_folder+'/'+location_rule.replace("'actor'","'超多人'",3).replace("actor","'超多人'",3) #path为影片+元数据所在目录
|
||||
#print(path)
|
||||
else:
|
||||
path = success_folder+'/'+location_rule
|
||||
#print(path)
|
||||
@@ -224,17 +263,19 @@ def imageDownload(filepath): #封面是否下载成功，否则移动到failed
|
||||
if DownloadFileWithFilename(cover, number + '.jpg', path) == 'failed':
|
||||
moveFailedFolder()
|
||||
DownloadFileWithFilename(cover, number + '.jpg', path)
|
||||
print('[+]Image Downloaded!', path + '/' + number + '.jpg')
|
||||
if multi_part == 1:
|
||||
old_name = os.path.join(path, number + '.jpg')
|
||||
new_name = os.path.join(path, number + part + '.jpg')
|
||||
os.rename(old_name, new_name)
|
||||
print('[+]Image Downloaded!', path + '/' + number + part + '.jpg')
|
||||
else:
|
||||
print('[+]Image Downloaded!', path + '/' + number + '.jpg')
|
||||
elif option == 'plex':
|
||||
if DownloadFileWithFilename(cover, 'fanart.jpg', path) == 'failed':
|
||||
moveFailedFolder()
|
||||
DownloadFileWithFilename(cover, 'fanart.jpg', path)
|
||||
print('[+]Image Downloaded!', path + '/fanart.jpg')
|
||||
def PrintFiles(filepath):
|
||||
#global path
|
||||
global title
|
||||
global cn_sub
|
||||
global actor_photo
|
||||
try:
|
||||
if not os.path.exists(path):
|
||||
os.makedirs(path)
|
||||
@@ -268,12 +309,12 @@ def PrintFiles(filepath):
|
||||
if cn_sub == '1':
|
||||
print(" <tag>中文字幕</tag>", file=code)
|
||||
try:
|
||||
for i in tag:
|
||||
for i in str(json_data['tag']).strip("[ ]").replace("'", '').replace(" ", '').split(','):
|
||||
print(" <tag>" + i + "</tag>", file=code)
|
||||
except:
|
||||
aaaaa = ''
|
||||
try:
|
||||
for i in tag:
|
||||
for i in str(json_data['tag']).strip("[ ]").replace("'", '').replace(" ", '').split(','):
|
||||
print(" <genre>" + i + "</genre>", file=code)
|
||||
except:
|
||||
aaaaaaaa = ''
|
||||
@@ -352,7 +393,7 @@ def cutImage():
|
||||
img2.save(path + '/poster.png')
|
||||
except:
|
||||
print('[-]Cover cut failed!')
|
||||
else:
|
||||
elif imagecut == 0:
|
||||
img = Image.open(path + '/fanart.jpg')
|
||||
w = img.width
|
||||
h = img.height
|
||||
@@ -368,7 +409,7 @@ def cutImage():
|
||||
img2.save(path + '/' + number + '.png')
|
||||
except:
|
||||
print('[-]Cover cut failed!')
|
||||
else:
|
||||
elif imagecut == 0:
|
||||
img = Image.open(path + '/' + number + '.jpg')
|
||||
w = img.width
|
||||
h = img.height
|
||||
@@ -382,15 +423,8 @@ def pasteFileToFolder(filepath, path): #文件路径，番号，后缀，要移
|
||||
print('[-]File Exists! Please check your movie!')
|
||||
print('[-]move to the root folder of the program.')
|
||||
os._exit(0)
|
||||
def pasteFileToFolder_mode2(filepath, path): #文件路径，番号，后缀，要移动至的位置
|
||||
global houzhui
|
||||
houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
|
||||
try:
|
||||
os.rename(filepath, path + houzhui)
|
||||
print('[+]Movie ' + number + ' move to target folder Finished!')
|
||||
except:
|
||||
print('[-]File Exists! Please check your movie!')
|
||||
print('[-]move to the root folder of the program.')
|
||||
except PermissionError:
|
||||
print('[-]Error! Please run as administrator!')
|
||||
os._exit(0)
|
||||
def renameJpgToBackdrop_copy():
|
||||
if option == 'plex':
|
||||
@@ -398,10 +432,40 @@ def renameJpgToBackdrop_copy():
|
||||
shutil.copy(path + '/poster.png', path + '/thumb.png')
|
||||
if option == 'emby':
|
||||
shutil.copy(path + '/' + number + '.jpg', path + '/Backdrop.jpg')
|
||||
|
||||
def renameBackdropToJpg_copy():
|
||||
if option == 'plex':
|
||||
shutil.copy(path + '/fanart.jpg', path + '/Backdrop.jpg')
|
||||
shutil.copy(path + '/poster.png', path + '/thumb.png')
|
||||
if option == 'emby':
|
||||
shutil.copy(path + '/Backdrop.jpg', path + '/' + number + '.jpg')
|
||||
print('[+]Image Downloaded!', path + '/' + number + '.jpg')
|
||||
def get_part(filepath):
|
||||
try:
|
||||
if re.search('-CD\d+', filepath):
|
||||
return re.findall('-CD\d+', filepath)[0]
|
||||
except:
|
||||
print("[-]failed!Please rename the filename again!")
|
||||
moveFailedFolder()
|
||||
def debug_mode():
|
||||
try:
|
||||
if config['debug_mode']['switch'] == '1':
|
||||
print('[+] ---Debug info---')
|
||||
for i, v in json_data.items():
|
||||
if i == 'outline':
|
||||
print('[+] -', i, ':', len(v), 'characters')
|
||||
continue
|
||||
if i == 'actor_photo' or i == 'year':
|
||||
continue
|
||||
print('[+] -', i, ':', v)
|
||||
print('[+] ---Debug info---')
|
||||
except:
|
||||
aaa=''
|
||||
if __name__ == '__main__':
|
||||
filepath=argparse_get_file()[0] #影片的路径
|
||||
|
||||
if '-CD' in filepath or '-cd' in filepath:
|
||||
multi_part = 1
|
||||
part = get_part(filepath)
|
||||
if '-c.' in filepath or '-C.' in filepath or '中文' in filepath or '字幕' in filepath:
|
||||
cn_sub='1'
|
||||
|
||||
@@ -416,12 +480,20 @@ if __name__ == '__main__':
|
||||
number = argparse_get_file()[1]
|
||||
CreatFailedFolder()
|
||||
getDataFromJSON(number) # 定义番号
|
||||
debug_mode()
|
||||
creatFolder() # 创建文件夹
|
||||
if program_mode == '1':
|
||||
imageDownload(filepath) # creatFoder会返回番号路径
|
||||
PrintFiles(filepath) # 打印文件
|
||||
cutImage() # 裁剪图
|
||||
if part == '-CD1' or multi_part == 0:
|
||||
smallCoverCheck()
|
||||
imageDownload(filepath) # creatFoder会返回番号路径
|
||||
if multi_part == 1:
|
||||
number += part
|
||||
PrintFiles(filepath) # 打印文件
|
||||
cutImage() # 裁剪图
|
||||
renameJpgToBackdrop_copy()
|
||||
else:
|
||||
number += part
|
||||
renameBackdropToJpg_copy()
|
||||
pasteFileToFolder(filepath, path) # 移动文件
|
||||
renameJpgToBackdrop_copy()
|
||||
elif program_mode == '2':
|
||||
pasteFileToFolder_mode2(filepath, path) # 移动文件
|
||||
pasteFileToFolder(filepath, path) # 移动文件
|
||||
|
||||
@@ -4,51 +4,43 @@ import json
|
||||
import ADC_function
|
||||
|
||||
def getTitle(htmlcode): #获取厂商
|
||||
#print(htmlcode)
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h3/text()')).strip(" ['']")
|
||||
result2 = str(re.sub('\D{2}2-\d+','',result)).replace(' ','',1)
|
||||
#print(result2)
|
||||
return result2
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/h2/text()')).strip(" ['']")
|
||||
return result
|
||||
def getActor(htmlcode):
|
||||
try:
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[5]/a/text()')).strip(" ['']")
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[5]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
def getStudio(htmlcode): #获取厂商
|
||||
html = etree.fromstring(htmlcode,etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[3]/a[1]/text()')).strip(" ['']")
|
||||
return result
|
||||
try:
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[5]/a/text()')).strip(" ['']")
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
def getNum(htmlcode): #获取番号
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
|
||||
#print(result)
|
||||
return result
|
||||
def getRelease(htmlcode2): #
|
||||
#a=ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
|
||||
html=etree.fromstring(htmlcode2,etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']")
|
||||
return result
|
||||
def getCover(htmlcode,number,htmlcode2): #获取厂商 #
|
||||
#a = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id=' + str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-") + '&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
|
||||
def getCover(htmlcode2): #获取厂商 #
|
||||
html = etree.fromstring(htmlcode2, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[1]/a/img/@src')).strip(" ['']")
|
||||
if result == '':
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result2 = str(html.xpath('//*[@id="slider"]/ul[1]/li[1]/img/@src')).strip(" ['']")
|
||||
return 'http://fc2fans.club' + result2
|
||||
return 'http:' + result
|
||||
def getOutline(htmlcode2,number): #获取番号 #
|
||||
#a = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id=' + str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-") + '&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
|
||||
def getOutline(htmlcode2): #获取番号 #
|
||||
html = etree.fromstring(htmlcode2, etree.HTMLParser())
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).replace("\\n",'',10000).strip(" ['']").replace("'",'',10000)
|
||||
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',')
|
||||
return result
|
||||
def getTag(htmlcode): #获取番号
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[4]/a/text()'))
|
||||
return result.strip(" ['']").replace("'",'').replace(' ','')
|
||||
result = html.xpath('//*[@id="container"]/div[1]/div/article/section[6]/ul/li/a/text()')
|
||||
return result
|
||||
def getYear(release):
|
||||
try:
|
||||
result = re.search('\d{4}',release).group()
|
||||
@@ -56,29 +48,28 @@ def getYear(release):
|
||||
except:
|
||||
return ''
|
||||
|
||||
def main(number2):
|
||||
number=number2.replace('PPV','').replace('ppv','')
|
||||
htmlcode2 = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
|
||||
htmlcode = ADC_function.get_html('http://fc2fans.club/html/FC2-' + number + '.html')
|
||||
def main(number):
|
||||
number=number.replace('PPV','').replace('ppv','').strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-').strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-').replace('fc2ppv-','').replace('FC2PPV-','')
|
||||
htmlcode2 = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'')
|
||||
#htmlcode = ADC_function.get_html('http://fc2fans.club/html/FC2-' + number + '.html')
|
||||
dic = {
|
||||
'title': getTitle(htmlcode),
|
||||
'studio': getStudio(htmlcode),
|
||||
'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
|
||||
'outline': getOutline(htmlcode,number),
|
||||
'runtime': getYear(getRelease(htmlcode)),
|
||||
'director': getStudio(htmlcode),
|
||||
'actor': getActor(htmlcode),
|
||||
'release': getRelease(number),
|
||||
'title': getTitle(htmlcode2),
|
||||
'studio': getStudio(htmlcode2),
|
||||
'year': getYear(getRelease(htmlcode2)),
|
||||
'outline': getOutline(htmlcode2),
|
||||
'runtime': getYear(getRelease(htmlcode2)),
|
||||
'director': getStudio(htmlcode2),
|
||||
'actor': getStudio(htmlcode2),
|
||||
'release': getRelease(htmlcode2),
|
||||
'number': 'FC2-'+number,
|
||||
'cover': getCover(htmlcode,number,htmlcode2),
|
||||
'cover': getCover(htmlcode2),
|
||||
'imagecut': 0,
|
||||
'tag': getTag(htmlcode),
|
||||
'tag': getTag(htmlcode2),
|
||||
'actor_photo':'',
|
||||
'website': 'http://fc2fans.club/html/FC2-' + number + '.html',
|
||||
'website': 'http://adult.contents.fc2.com/article_search.php?id=' + number,
|
||||
'source': 'fc2fans_club.py',
|
||||
}
|
||||
#print(getTitle(htmlcode))
|
||||
#print(getNum(htmlcode))
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
|
||||
return js
|
||||
|
||||
#print(main('1051725'))
|
||||
#print(main('1145465'))
|
||||
53
javbus.py
53
javbus.py
@@ -1,17 +1,9 @@
|
||||
import re
|
||||
import requests #need install
|
||||
from pyquery import PyQuery as pq#need install
|
||||
from lxml import etree#need install
|
||||
import os
|
||||
import os.path
|
||||
import shutil
|
||||
from bs4 import BeautifulSoup#need install
|
||||
from PIL import Image#need install
|
||||
import time
|
||||
import json
|
||||
from ADC_function import *
|
||||
import javdb
|
||||
import siro
|
||||
|
||||
def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
|
||||
soup = BeautifulSoup(htmlcode, 'lxml')
|
||||
@@ -88,16 +80,12 @@ def getTag(htmlcode): # 获取演员
|
||||
|
||||
|
||||
def main(number):
|
||||
try:
|
||||
if re.search('\d+\D+', number).group() in number:
|
||||
js = siro.main(number)
|
||||
return js
|
||||
except:
|
||||
aaaa=''
|
||||
|
||||
try:
|
||||
htmlcode = get_html('https://www.javbus.com/' + number)
|
||||
dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
|
||||
try:
|
||||
dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
|
||||
except:
|
||||
dww_htmlcode = ''
|
||||
dic = {
|
||||
'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
|
||||
'studio': getStudio(htmlcode),
|
||||
@@ -114,35 +102,12 @@ def main(number):
|
||||
'label': getSerise(htmlcode),
|
||||
'actor_photo': getActorPhoto(htmlcode),
|
||||
'website': 'https://www.javbus.com/' + number,
|
||||
'source' : 'javbus.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
if 'HEYZO' in number or 'heyzo' in number or 'Heyzo' in number:
|
||||
htmlcode = get_html('https://www.javbus.com/' + number)
|
||||
#dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
|
||||
dic = {
|
||||
'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
|
||||
'studio': getStudio(htmlcode),
|
||||
'year': getYear(htmlcode),
|
||||
'outline': '',
|
||||
'runtime': getRuntime(htmlcode),
|
||||
'director': getDirector(htmlcode),
|
||||
'actor': getActor(htmlcode),
|
||||
'release': getRelease(htmlcode),
|
||||
'number': getNum(htmlcode),
|
||||
'cover': getCover(htmlcode),
|
||||
'imagecut': 1,
|
||||
'tag': getTag(htmlcode),
|
||||
'label': getSerise(htmlcode),
|
||||
'actor_photo': getActorPhoto(htmlcode),
|
||||
'website': 'https://www.javbus.com/' + number,
|
||||
}
|
||||
js2 = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,
|
||||
separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js2
|
||||
return js
|
||||
except:
|
||||
a=javdb.main(number)
|
||||
return a
|
||||
return main_uncensored(number)
|
||||
|
||||
def main_uncensored(number):
|
||||
htmlcode = get_html('https://www.javbus.com/' + number)
|
||||
@@ -166,11 +131,7 @@ def main_uncensored(number):
|
||||
'imagecut': 0,
|
||||
'actor_photo': '',
|
||||
'website': 'https://www.javbus.com/' + number,
|
||||
'source': 'javbus.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
|
||||
if getYear(htmlcode) == '' or getYear(htmlcode) == 'null':
|
||||
js2 = javdb.main(number)
|
||||
return js2
|
||||
|
||||
return js
|
||||
17
javdb.py
17
javdb.py
@@ -1,7 +1,6 @@
|
||||
import re
|
||||
from lxml import etree
|
||||
import json
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from ADC_function import *
|
||||
|
||||
@@ -79,7 +78,6 @@ def main(number):
|
||||
result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
|
||||
b = get_html('https://javdb1.com' + result1)
|
||||
soup = BeautifulSoup(b, 'lxml')
|
||||
|
||||
a = str(soup.find(attrs={'class': 'panel'}))
|
||||
dic = {
|
||||
'actor': getActor(a),
|
||||
@@ -99,6 +97,7 @@ def main(number):
|
||||
'year': getYear(getRelease(a)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': '',
|
||||
'website': 'https://javdb1.com' + result1,
|
||||
'source': 'javdb.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
@@ -106,19 +105,18 @@ def main(number):
|
||||
a = get_html('https://javdb.com/search?q=' + number + '&f=all')
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
|
||||
if result1 == '':
|
||||
if result1 == '' or result1 == 'null':
|
||||
a = get_html('https://javdb.com/search?q=' + number.replace('-', '_') + '&f=all')
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
|
||||
|
||||
b = get_html('https://javdb.com' + result1)
|
||||
soup = BeautifulSoup(b, 'lxml')
|
||||
|
||||
a = str(soup.find(attrs={'class': 'panel'}))
|
||||
dic = {
|
||||
'actor': getActor(a),
|
||||
'title': getTitle(b).replace("\\n", '').replace(' ', '').replace(getActor(a), '').replace(getNum(a),
|
||||
'').replace(
|
||||
'title': getTitle(b).replace("\\n", '').replace(' ', '').replace(getActor(a), '').replace(
|
||||
getNum(a),
|
||||
'').replace(
|
||||
'无码', '').replace('有码', '').lstrip(' '),
|
||||
'studio': getStudio(a),
|
||||
'outline': getOutline(a),
|
||||
@@ -132,9 +130,10 @@ def main(number):
|
||||
'label': getLabel(a),
|
||||
'year': getYear(getRelease(a)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': '',
|
||||
'website':'https://javdb.com' + result1,
|
||||
'website': 'https://javdb.com' + result1,
|
||||
'source': 'javdb.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
|
||||
#print(main('061519-861'))
|
||||
2
siro.py
2
siro.py
@@ -1,7 +1,6 @@
|
||||
import re
|
||||
from lxml import etree
|
||||
import json
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from ADC_function import *
|
||||
|
||||
@@ -97,6 +96,7 @@ def main(number2):
|
||||
'year': getYear(getRelease(a)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': '',
|
||||
'website':'https://www.mgstage.com/product/product_detail/'+str(number)+'/',
|
||||
'source': 'siro.py',
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
|
||||
return js
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"version": "0.11.9",
|
||||
"version_show":"Beta 11.9",
|
||||
"version": "1.3",
|
||||
"version_show":"1.3",
|
||||
"download": "https://github.com/wenead99/AV_Data_Capture/releases"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user