diff --git a/ADC_function.py b/ADC_function.py
index 0a3b4ed..1c679ed 100644
--- a/ADC_function.py
+++ b/ADC_function.py
@@ -2,6 +2,8 @@ import requests
from configparser import RawConfigParser
import os
import re
+from retrying import retry
+import sys
# content = open('proxy.ini').read()
# content = re.sub(r"\xfe\xff","", content)
@@ -16,27 +18,52 @@ else:
with open("proxy.ini", "wt", encoding='UTF-8') as code:
print("[proxy]",file=code)
print("proxy=127.0.0.1:1080",file=code)
-
+ print("timeout=10", file=code)
+ print("[Name_Rule]", file=code)
+ print("location_rule='JAV_output/'+actor+'/['+number+']-'+title",file=code)
+ print("naming_rule=number+'-'+title",file=code)
+ print("[update]",file=code)
+ print("update_check=1")
+def UpdateCheckSwitch():
+ check=str(config['update']['update_check'])
+ if check == '1':
+ return '1'
+ elif check == '0':
+ return '0'
def get_html(url,cookies = None):#网页请求核心
- if not str(config['proxy']['proxy']) == '':
- proxies = {
- "http" : "http://" + str(config['proxy']['proxy']),
- "https": "https://" + str(config['proxy']['proxy'])
- }
- headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'}
- getweb = requests.get(str(url), headers=headers, proxies=proxies,cookies=cookies)
- getweb.encoding = 'utf-8'
- # print(getweb.text)
+ i = 0
+ retry_count = int(config['proxy']['retry'])
+ while i < retry_count:
try:
- return getweb.text
- except:
- print('[-]Connected failed!:Proxy error')
- else:
- headers = {
- 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
- getweb = requests.get(str(url), headers=headers,cookies=cookies)
- getweb.encoding = 'utf-8'
- try:
- return getweb.text
- except:
- print("[-]Connect Failed.")
\ No newline at end of file
+ if not str(config['proxy']['proxy']) == '':
+ proxies = {
+ "http": "http://" + str(config['proxy']['proxy']),
+ "https": "https://" + str(config['proxy']['proxy'])
+ }
+ headers = {
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'}
+ getweb = requests.get(str(url), headers=headers, timeout=int(config['proxy']['timeout']),proxies=proxies, cookies=cookies)
+ getweb.encoding = 'utf-8'
+ # print(getweb.text)
+ return getweb.text
+ else:
+ headers = {
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
+ getweb = requests.get(str(url), headers=headers,timeout=int(config['proxy']['timeout']), cookies=cookies)
+ getweb.encoding = 'utf-8'
+ return getweb.text
+ except requests.exceptions.RequestException:
+ i += 1
+ print('[-]Connect retry '+str(i)+'/'+str(retry_count))
+ except requests.exceptions.ConnectionError:
+ i += 1
+ print('[-]Connect retry '+str(i)+'/'+str(retry_count))
+ except requests.exceptions.ProxyError:
+ i += 1
+ print('[-]Connect retry '+str(i)+'/'+str(retry_count))
+ except requests.exceptions.ConnectTimeout:
+ i += 1
+ print('[-]Connect retry '+str(i)+'/'+str(retry_count))
+
+
+
diff --git a/AV_Data_Capture.py b/AV_Data_Capture.py
index b1c2823..dd0127b 100644
--- a/AV_Data_Capture.py
+++ b/AV_Data_Capture.py
@@ -3,48 +3,57 @@ import os
import time
import re
import sys
-from ADC_function import *
+import ADC_function
import json
+import shutil
-version='0.10.6'
+version='0.11.1'
+os.chdir(os.getcwd())
def UpdateCheck():
- html2 = get_html('https://raw.githubusercontent.com/wenead99/AV_Data_Capture/master/update_check.json')
- html = json.loads(str(html2))
-
- if not version == html['version']:
- print('[*] * New update '+html['version']+' *')
- print('[*] * Download *')
- print('[*] '+html['download'])
- print('[*]=====================================')
+ if ADC_function.UpdateCheckSwitch() == '1':
+ html2 = ADC_function.get_html('https://raw.githubusercontent.com/wenead99/AV_Data_Capture/master/update_check.json')
+ html = json.loads(str(html2))
+ if not version == html['version']:
+ print('[*] * New update ' + html['version'] + ' *')
+ print('[*] * Download *')
+ print('[*] ' + html['download'])
+ print('[*]=====================================')
+ else:
+ print('[+]Update Check disabled!')
def movie_lists():
#MP4
- a2 = glob.glob(os.getcwd() + r"\*.mp4")
+ a2 = glob.glob(r".\*.mp4")
# AVI
- b2 = glob.glob(os.getcwd() + r"\*.avi")
+ b2 = glob.glob(r".\*.avi")
# RMVB
- c2 = glob.glob(os.getcwd() + r"\*.rmvb")
+ c2 = glob.glob(r".\*.rmvb")
# WMV
- d2 = glob.glob(os.getcwd() + r"\*.wmv")
+ d2 = glob.glob(r".\*.wmv")
# MOV
- e2 = glob.glob(os.getcwd() + r"\*.mov")
+ e2 = glob.glob(r".\*.mov")
# MKV
- f2 = glob.glob(os.getcwd() + r"\*.mkv")
+ f2 = glob.glob(r".\*.mkv")
# FLV
- g2 = glob.glob(os.getcwd() + r"\*.flv")
+ g2 = glob.glob(r".\*.flv")
# TS
- h2 = glob.glob(os.getcwd() + r"\*.ts")
+ h2 = glob.glob(r".\*.ts")
total = a2+b2+c2+d2+e2+f2+g2+h2
return total
-
+def CreatFailedFolder():
+ if not os.path.exists('failed/'): # 新建failed文件夹
+ try:
+ os.makedirs('failed/')
+ except:
+ print("[-]failed!can not be make folder 'failed'\n[-](Please run as Administrator)")
+ os._exit(0)
def lists_from_test(custom_nuber): #电影列表
a=[]
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:
@@ -53,29 +62,74 @@ def CEF(path):
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)
if max and str(max[0]).isdigit():
count = max[0]
return new.join(self.rsplit(old, count))
+def getNumber(filepath):
+ try: # 试图提取番号
+ # ====番号获取主程序====
+ 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()
+ if '-C.' in filepath or '-c.' in filepath:
+ cn_sub = '1'
+ 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))
+ 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() + '-'))
+ return file_number
+ # if not re.search('\w-', file_number).group() == 'None':
+ # file_number = re.search('\w+-\w+', filename).group()
+ # 上面是插入减号-到番号中
+ # ====番号获取主程序=结束===
+ except Exception as e: # 番号提取异常
+ print('[-]' + str(os.path.basename(filepath)) + ' Cannot catch the number :')
+ print('[-]' + str(os.path.basename(filepath)) + ' :', e)
+ print('[-]Move ' + os.path.basename(filepath) + ' to failed folder')
+ shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
+ except IOError as e2:
+ print('[-]' + str(os.path.basename(filepath)) + ' Cannot catch the number :')
+ print('[-]' + str(os.path.basename(filepath)) + ' :', e2)
+ print('[-]Move ' + os.path.basename(filepath) + ' to failed folder')
+ shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
if __name__ =='__main__':
print('[*]===========AV Data Capture===========')
print('[*] Version '+version)
print('[*]=====================================')
+ CreatFailedFolder()
UpdateCheck()
os.chdir(os.getcwd())
+
+ count = 0
+ count_all = str(len(movie_lists()))
for i in movie_lists(): #遍历电影列表 交给core处理
- if '_' in i:
- os.rename(re.search(r'[^\\/:*?"<>|\r\n]+$', i).group(), rreplace(re.search(r'[^\\/:*?"<>|\r\n]+$', i).group(), '_', '-', 1))
- i = rreplace(re.search(r'[^\\/:*?"<>|\r\n]+$', i).group(), '_', '-', 1)
- os.system('python core.py' + ' "' + i + '"') #选择从py文件启动 （用于源码py）
- #os.system('core.exe' + ' "' + i + '"') #选择从exe文件启动（用于EXE版程序）
+ count = count + 1
+ percentage = str(count/int(count_all)*100)[:4]+'%'
+ print('[!] - '+percentage+' ['+str(count)+'/'+count_all+'] -')
+ print("[!]Making Data for [" + i + "],the number is [" + getNumber(i) + "]")
+ os.system('python core.py' + ' "' + i + '" --number "'+getNumber(i)+'"') #选择从py文件启动 （用于源码py）
+ #os.system('core.exe' + ' "' + i + '" --number "'+getNumber(i)+'"') #选择从exe文件启动（用于EXE版程序）
print("[*]=====================================")
- print("[!]Cleaning empty folders")
CEF('JAV_output')
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错误信息。")
+ 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。")
\ No newline at end of file
diff --git a/core.py b/core.py
index c187076..4e4971a 100644
--- a/core.py
+++ b/core.py
@@ -10,6 +10,8 @@ import fc2fans_club
import siro
from ADC_function import *
from configparser import ConfigParser
+import argparse
+import javdb
#初始化全局变量
title=''
@@ -25,15 +27,19 @@ number=''
cover=''
imagecut=''
tag=[]
+cn_sub=''
+path=''
+houzhui=''
naming_rule =''#eval(config['Name_Rule']['naming_rule'])
location_rule=''#eval(config['Name_Rule']['location_rule'])
+
#=====================本地文件处理===========================
def argparse_get_file():
- import argparse
parser = argparse.ArgumentParser()
+ parser.add_argument("--number", help="Enter Number on here", default='')
parser.add_argument("file", help="Write the file path on here")
args = parser.parse_args()
- return args.file
+ return (args.file, args.number)
def CreatFailedFolder():
if not os.path.exists('failed/'): # 新建failed文件夹
try:
@@ -41,7 +47,7 @@ def CreatFailedFolder():
except:
print("[-]failed!can not be make folder 'failed'\n[-](Please run as Administrator)")
os._exit(0)
-def getNumberFromFilename(filepath):
+def getDataFromJSON(file_number): #从JSON返回元数据
global title
global studio
global year
@@ -56,106 +62,72 @@ def getNumberFromFilename(filepath):
global imagecut
global tag
global image_main
+ global cn_sub
global naming_rule
global location_rule
-#================================================获取文件番号================================================
- try: #试图提取番号
- # ====番号获取主程序====
- try: # 普通提取番号 主要处理包含减号-的番号
- filepath.strip('22-sht.me').strip('-HD').strip('-hd')
- filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath)) # 去除文件名中文件名
- file_number = re.search('\w+-\d+', filename).group()
- 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('_')
- file_number = str(re.search('n\d{4}', filename0).group(0))
- 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())
- file_number = str(file_number2.replace(re.match("^[A-Za-z]+", file_number2).group(),re.match("^[A-Za-z]+", file_number2).group() + '-'))
- #if not re.search('\w-', file_number).group() == 'None':
- #file_number = re.search('\w+-\w+', filename).group()
- #上面是插入减号-到番号中
- print("[!]Making Data for [" + filename + "],the number is [" + file_number + "]")
- # ====番号获取主程序=结束===
- except Exception as e: #番号提取异常
- print('[-]'+str(os.path.basename(filepath))+' Cannot catch the number :')
- print('[-]' + str(os.path.basename(filepath)) + ' :', e)
- print('[-]Move ' + os.path.basename(filepath) + ' to failed folder')
- shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
- os._exit(0)
- except IOError as e2:
- print('[-]' + str(os.path.basename(filepath)) + ' Cannot catch the number :')
- print('[-]' + str(os.path.basename(filepath)) + ' :',e2)
- print('[-]Move ' + os.path.basename(filepath) + ' to failed folder')
- shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
- os._exit(0)
- try:
+ 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(javdb.main(file_number))
+ # ======================siro.py==========================
+ elif re.search('\d+\D+', file_number).group() in file_number:
+ json_data = json.loads(siro.main(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-')))
+ # print(file_number.strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-'))
+ # =======================javbus.py=======================
+ else:
+ json_data = json.loads(javbus.main(file_number))
+ # ================================================网站规则添加结束================================================
+ title = str(json_data['title'])
+ studio = json_data['studio']
+ year = json_data['year']
+ outline = json_data['outline']
+ runtime = json_data['runtime']
+ director = json_data['director']
+ actor_list = str(json_data['actor']).strip("[ ]").replace("'", '').replace(" ", '').split(',') # 字符串转列表
+ release = json_data['release']
+ number = json_data['number']
+ cover = json_data['cover']
+ imagecut = json_data['imagecut']
+ tag = str(json_data['tag']).strip("[ ]").replace("'", '').replace(" ", '').split(',') # 字符串转列表
+ actor = str(actor_list).strip("[ ]").replace("'", '').replace(" ", '')
+ # ====================处理异常字符====================== #\/:*?"<>|
+ if '\\' 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('<', '')
+ elif '>' in title:
+ title=title.replace('>', '')
+ elif '|' in title:
+ title=title.replace('|', '')
+ # ====================处理异常字符 END================== #\/:*?"<>|
-# ================================================网站规则添加开始================================================
+ naming_rule = eval(config['Name_Rule']['naming_rule'])
+ location_rule = eval(config['Name_Rule']['location_rule'])
- try: #添加 需要 正则表达式的规则
- #=======================javbus.py=======================
- if re.search('^\d{5,}', file_number).group() in filename:
- 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 filename:
- 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 filename:
- 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-')))
- #print(file_number.strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-'))
- #=======================javbus.py=======================
- else:
- json_data = json.loads(javbus.main(file_number))
-
-
-
-#================================================网站规则添加结束================================================
-
-
-
-
- title = json_data['title']
- studio = json_data['studio']
- year = json_data['year']
- outline = json_data['outline']
- runtime = json_data['runtime']
- director = json_data['director']
- actor_list = str(json_data['actor']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表
- release = json_data['release']
- number = json_data['number']
- cover = json_data['cover']
- imagecut = json_data['imagecut']
- tag = str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表
- actor = str(actor_list).strip("[ ]").replace("'",'').replace(" ",'')
-
- #====================处理异常字符====================== #\/:*?"<>|
- #if "\\" in title or "/" in title or ":" in title or "*" in title or "?" in title or '"' in title or '<' in title or ">" in title or "|" in title or len(title) > 200:
- # title = title.
-
- naming_rule = eval(config['Name_Rule']['naming_rule'])
- location_rule =eval(config['Name_Rule']['location_rule'])
- except IOError as e:
- print('[-]'+str(e))
- print('[-]Move ' + filename + ' to failed folder')
- shutil.move(filepath, str(os.getcwd())+'/'+'failed/')
- os._exit(0)
-
- except Exception as e:
- print('[-]'+str(e))
- print('[-]Move ' + filename + ' to failed folder')
- shutil.move(filepath, str(os.getcwd())+'/'+'failed/')
- os._exit(0)
-path = '' #设置path为全局变量，后面移动文件要用
-def creatFolder():
+def creatFolder(): #创建文件夹
global actor
global path
if len(actor) > 240: #新建成功输出文件夹
@@ -168,56 +140,62 @@ def creatFolder():
try:
os.makedirs(path)
except:
- path = location_rule.replace(actor,"'其他'")
+ path = location_rule.replace('/['+number+']-'+title,"/number")
+ #print(path)
os.makedirs(path)
-
-
#=====================资源下载部分===========================
def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder!
config = ConfigParser()
config.read('proxy.ini', encoding='UTF-8')
proxy = str(config['proxy']['proxy'])
- if not str(config['proxy']['proxy']) == '':
+ timeout = int(config['proxy']['timeout'])
+ retry_count = int(config['proxy']['retry'])
+ i = 0
+ while i < retry_count:
try:
- if not os.path.exists(path):
- os.makedirs(path)
- headers = {
- 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
- r = requests.get(url, headers=headers,proxies={"http": "http://" + str(proxy), "https": "https://" + str(proxy)})
- with open(str(path) + "/" + filename, "wb") as code:
- code.write(r.content)
- # print(bytes(r),file=code)
- except IOError as e:
- print("[-]Movie not found in All website!")
- print("[-]" + filename, e)
- # print("[*]=====================================")
- return "failed"
- except Exception as e1:
- print(e1)
- print("[-]Download Failed2!")
- time.sleep(3)
- os._exit(0)
- else:
- try:
- if not os.path.exists(path):
- os.makedirs(path)
- headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
- r = requests.get(url, headers=headers)
- with open(str(path) + "/" + filename, "wb") as code:
- code.write(r.content)
- # print(bytes(r),file=code)
- except IOError as e:
- print("[-]Movie not found in All website!")
- print("[-]" + filename, e)
- # print("[*]=====================================")
- return "failed"
- except Exception as e1:
- print(e1)
- print("[-]Download Failed2!")
- time.sleep(3)
- os._exit(0)
-def PrintFiles(path,naming_rule):
+ if not str(config['proxy']['proxy']) == '':
+ if not os.path.exists(path):
+ os.makedirs(path)
+ headers = {
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
+ r = requests.get(url, headers=headers, timeout=timeout,proxies={"http": "http://" + str(proxy), "https": "https://" + str(proxy)})
+ with open(str(path) + "/" + filename, "wb") as code:
+ code.write(r.content)
+ return
+ # print(bytes(r),file=code)
+ else:
+ if not os.path.exists(path):
+ os.makedirs(path)
+ headers = {
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
+ r = requests.get(url, timeout=timeout, headers=headers)
+ with open(str(path) + "/" + filename, "wb") as code:
+ code.write(r.content)
+ return
+ # print(bytes(r),file=code)
+ except requests.exceptions.RequestException:
+ i += 1
+ print('[-]Image Download : Connect retry '+str(i)+'/'+str(retry_count))
+ except requests.exceptions.ConnectionError:
+ i += 1
+ print('[-]Image Download : Connect retry '+str(i)+'/'+str(retry_count))
+ except requests.exceptions.ProxyError:
+ i += 1
+ print('[-]Image Download : Connect retry '+str(i)+'/'+str(retry_count))
+ except requests.exceptions.ConnectTimeout:
+ i += 1
+ print('[-]Image Download : Connect retry '+str(i)+'/'+str(retry_count))
+def imageDownload(filepath): #封面是否下载成功，否则移动到failed
+ global path
+ if DownloadFileWithFilename(cover,naming_rule+'.jpg', path) == 'failed':
+ shutil.move(filepath, 'failed/')
+ os._exit(0)
+ DownloadFileWithFilename(cover, naming_rule+'.jpg', path)
+ print('[+]Image Downloaded!', path +'/'+naming_rule+'.jpg')
+def PrintFiles(filepath):
+ #global path
global title
+ global cn_sub
try:
if not os.path.exists(path):
os.makedirs(path)
@@ -245,6 +223,8 @@ def PrintFiles(path,naming_rule):
print(" <maker>" + studio + "</maker>", file=code)
print(" <label>", file=code)
print(" </label>", file=code)
+ if cn_sub == '1':
+ print(" <tag>中文字幕</tag>", file=code)
try:
for i in tag:
print(" <tag>" + i + "</tag>", file=code)
@@ -255,6 +235,8 @@ def PrintFiles(path,naming_rule):
print(" <genre>" + i + "</genre>", file=code)
except:
aaaaaaaa=''
+ if cn_sub == '1':
+ print(" <genre>中文字幕</genre>", file=code)
print(" <num>" + number + "</num>", file=code)
print(" <release>" + release + "</release>", file=code)
print(" <cover>"+cover+"</cover>", file=code)
@@ -264,42 +246,61 @@ def PrintFiles(path,naming_rule):
except IOError as e:
print("[-]Write Failed!")
print(e)
+ shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
+ os._exit(0)
except Exception as e1:
print(e1)
print("[-]Write Failed!")
-def imageDownload(filepath): #封面是否下载成功，否则移动到failed
- if DownloadFileWithFilename(cover,'Backdrop.jpg', path) == 'failed':
- shutil.move(filepath, 'failed/')
+ shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
os._exit(0)
- DownloadFileWithFilename(cover, 'Backdrop.jpg', path)
- print('[+]Image Downloaded!', path +'/'+'Backdrop.jpg')
def cutImage():
if imagecut == 1:
try:
- img = Image.open(path + '/' + 'Backdrop' + '.jpg')
+ img = Image.open(path + '/' + naming_rule + '.jpg')
imgSize = img.size
w = img.width
h = img.height
img2 = img.crop((w / 1.9, 0, w, h))
- img2.save(path + '/' + number + '.png')
+ img2.save(path + '/' + naming_rule + '.png')
except:
print('[-]Cover cut failed!')
else:
- img = Image.open(path + '/' + 'Backdrop' + '.jpg')
+ img = Image.open(path + '/' + naming_rule + '.jpg')
w = img.width
h = img.height
- img.save(path + '/' + number + '.png')
+ img.save(path + '/' + naming_rule + '.png')
def pasteFileToFolder(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)$', filepath).group())
- os.rename(filepath, number + houzhui)
- shutil.move(number + houzhui, path)
+ os.rename(filepath, naming_rule + houzhui)
+ shutil.move(naming_rule + houzhui, path)
+def renameJpgToBackdrop_copy():
+ shutil.copy(path+'/'+naming_rule + '.jpg', path+'/Backdrop.jpg')
if __name__ == '__main__':
- filepath=argparse_get_file() #影片的路径
- CreatFailedFolder()
- getNumberFromFilename(filepath) #定义番号
- creatFolder() #创建文件夹
- imageDownload(filepath) #creatFoder会返回番号路径
- PrintFiles(path,naming_rule)#打印文件
- cutImage() #裁剪图
- pasteFileToFolder(filepath,path) #移动文件
+ filepath=argparse_get_file()[0] #影片的路径
+
+ if argparse_get_file()[1] == '': #获取手动拉去影片获取的番号
+ try:
+ number = str(re.findall(r'(.+?)\.',str(re.search('([^<>/\\\\|:""\\*\\?]+)\\.\\w+$',filepath).group()))).strip("['']").replace('_','-')
+ print("[!]Making Data for [" + number + "]")
+ except:
+ print("[-]failed!Please rename the filename again!")
+ shutil.move(filepath,'failed/')
+ else:
+ number = argparse_get_file()[1]
+
+ try:
+ CreatFailedFolder()
+ getDataFromJSON(number) # 定义番号
+ creatFolder() # 创建文件夹
+ imageDownload(filepath) # creatFoder会返回番号路径
+ PrintFiles(filepath) # 打印文件
+ cutImage() # 裁剪图
+ pasteFileToFolder(filepath, path) # 移动文件
+ renameJpgToBackdrop_copy()
+ #time.sleep(20)
+ except:
+ print('[-]Movie data capture failed!')
+ #time.sleep(20)
+ os._exit(0)
diff --git a/fc2fans_club.py b/fc2fans_club.py
index 39c0647..d966b49 100644
--- a/fc2fans_club.py
+++ b/fc2fans_club.py
@@ -17,7 +17,6 @@ def getActor(htmlcode):
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(" ['']")
@@ -41,7 +40,6 @@ def getCover(htmlcode,number,htmlcode2): #获取厂商 #
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')
html = etree.fromstring(htmlcode2, etree.HTMLParser())
diff --git a/javbus.py b/javbus.py
index d452717..2f284f7 100644
--- a/javbus.py
+++ b/javbus.py
@@ -10,7 +10,7 @@ from PIL import Image#need install
import time
import json
from ADC_function import *
-import siro
+import javdb
def getTitle(htmlcode): #获取标题
doc = pq(htmlcode)
@@ -118,7 +118,7 @@ def main(number):
return js2
return js
except:
- a=siro.main(number)
+ a=javdb.main(number)
return a
def main_uncensored(number):
@@ -142,53 +142,7 @@ def main_uncensored(number):
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
if getYear(htmlcode) == '' or getYear(htmlcode) == 'null':
- number2 = number.replace('-', '_')
- htmlcode = get_html('https://www.javbus.com/' + number2)
- dic2 = {
- 'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(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),
- 'tag': getTag(htmlcode),
- 'label':getSerise(htmlcode),
- 'imagecut': 0,
- }
- js2 = json.dumps(dic2, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
+ js2 = javdb.main(number)
return js2
- return js
-
-
-# def return1():
-# json_data=json.loads(main('ipx-292'))
-#
-# title = str(json_data['title'])
-# studio = str(json_data['studio'])
-# year = str(json_data['year'])
-# outline = str(json_data['outline'])
-# runtime = str(json_data['runtime'])
-# director = str(json_data['director'])
-# actor = str(json_data['actor'])
-# release = str(json_data['release'])
-# number = str(json_data['number'])
-# cover = str(json_data['cover'])
-# tag = str(json_data['tag'])
-#
-# print(title)
-# print(studio)
-# print(year)
-# print(outline)
-# print(runtime)
-# print(director)
-# print(actor)
-# print(release)
-# print(number)
-# print(cover)
-# print(tag)
-# return1()
\ No newline at end of file
+ return js
\ No newline at end of file
diff --git a/javdb.py b/javdb.py
new file mode 100644
index 0000000..17023a3
--- /dev/null
+++ b/javdb.py
@@ -0,0 +1,133 @@
+import re
+from lxml import etree
+import json
+import requests
+from bs4 import BeautifulSoup
+from ADC_function import *
+
+def getTitle(a):
+ try:
+ html = etree.fromstring(a, etree.HTMLParser())
+ result = str(html.xpath('/html/body/section/div/h2/strong/text()')).strip(" ['']")
+ return re.sub('.*\] ','',result.replace('/', ',').replace('\\xa0','').replace(' : ',''))
+ except:
+ return re.sub('.*\] ','',result.replace('/', ',').replace('\\xa0',''))
+def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
+ html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/text()')).strip(" ['']")
+ result2 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/a/text()')).strip(" ['']")
+ return str(result1 + result2).strip('+').replace(",\\xa0","").replace("'","").replace(' ','').replace(',,','').lstrip(',').replace(',',', ')
+def getStudio(a):
+ html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//strong[contains(text(),"製作")]/../following-sibling::span/text()')).strip(" ['']")
+ result2 = str(html.xpath('//strong[contains(text(),"製作")]/../following-sibling::span/a/text()')).strip(" ['']")
+ return str(result1+result2).strip('+').replace("', '",'').replace('"','')
+def getRuntime(a):
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/text()')).strip(" ['']")
+ result2 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/a/text()')).strip(" ['']")
+ return str(result1 + result2).strip('+').rstrip('mi')
+def getLabel(a):
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/text()')).strip(" ['']")
+ result2 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/a/text()')).strip(" ['']")
+ return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
+def getNum(a):
+ html = etree.fromstring(a, etree.HTMLParser())
+ result1 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/text()')).strip(" ['']")
+ result2 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/a/text()')).strip(" ['']")
+ return str(result1 + result2).strip('+')
+def getYear(getRelease):
+ try:
+ result = str(re.search('\d{4}',getRelease).group())
+ return result
+ except:
+ return getRelease
+def getRelease(a):
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/text()')).strip(" ['']")
+ result2 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/a/text()')).strip(" ['']")
+ return str(result1 + result2).strip('+')
+def getTag(a):
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/text()')).strip(" ['']")
+ result2 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/a/text()')).strip(" ['']")
+ return str(result1 + result2).strip('+').replace(",\\xa0","").replace("'","").replace(' ','').replace(',,','').lstrip(',')
+def getCover(htmlcode):
+ html = etree.fromstring(htmlcode, etree.HTMLParser())
+ result = str(html.xpath('/html/body/section/div/div[2]/div[1]/a/img/@src')).strip(" ['']")
+ return result
+def getDirector(a):
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/text()')).strip(" ['']")
+ result2 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/a/text()')).strip(" ['']")
+ return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
+def getOutline(htmlcode):
+ html = etree.fromstring(htmlcode, etree.HTMLParser())
+ result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
+ return result
+def main(number):
+ try:
+ try:
+ a = get_html('https://javdb1.com/search?q=' + number + '&f=all')
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ except:
+ a = get_html('https://javdb1.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://javdb1.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(
+ '无码', '').replace('有码', '').lstrip(' '),
+ 'studio': getStudio(a),
+ 'outline': getOutline(a),
+ 'runtime': getRuntime(a),
+ 'director': getDirector(a),
+ 'release': getRelease(a),
+ 'number': getNum(a),
+ 'cover': getCover(b),
+ 'imagecut': 0,
+ 'tag': getTag(a),
+ 'label': getLabel(a),
+ 'year': getYear(getRelease(a)), # str(re.search('\d{4}',getRelease(a)).group()),
+ }
+ js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
+ return js
+ except:
+ try:
+ a = get_html('https://javdb.com/search?q=' + number + '&f=all')
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ except:
+ 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(
+ '无码', '').replace('有码', '').lstrip(' '),
+ 'studio': getStudio(a),
+ 'outline': getOutline(a),
+ 'runtime': getRuntime(a),
+ 'director': getDirector(a),
+ 'release': getRelease(a),
+ 'number': getNum(a),
+ 'cover': getCover(b),
+ 'imagecut': 0,
+ 'tag': getTag(a),
+ 'label': getLabel(a),
+ 'year': getYear(getRelease(a)), # str(re.search('\d{4}',getRelease(a)).group()),
+ }
+ js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
+ return js
+
+#print(main('061519-861'))
\ No newline at end of file