tanpengsccd/AV_Data_Capture
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add files via upload

Browse Source
This commit is contained in:
wenead99 2019-06-22 19:20:54 +08:00 committed by GitHub
parent 9ec99143d4
commit 908da6d006
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 19 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
AV_Data_Capture.py
View File

@ -71,8 +71,8 @@ if __name__ =='__main__':
if '_' in i: if '_' in i:
os.rename(re.search(r'[^\\/:*?"<>|\r\n]+$', i).group(), rreplace(re.search(r'[^\\/:*?"<>|\r\n]+$', i).group(), '_', '-', 1)) 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]+$', i).group(), '_', '-', 1) i = rreplace(re.search(r'[^\\/:*?"<>|\r\n]+$', i).group(), '_', '-', 1)
os.system('python core.py' + ' "' + i + '"') #选择从py文件启动 （用于源码py） #os.system('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） os.system('core.exe' + ' "' + i + '"') #选择从exe文件启动（用于EXE版程序）
print("[*]=====================================") print("[*]=====================================")
print("[!]Cleaning empty folders") print("[!]Cleaning empty folders")

13
core.py
View File

@ -108,9 +108,9 @@ def getNumberFromFilename(filepath):
except: #添加 无需 正则表达式的规则 except: #添加 无需 正则表达式的规则
# ====================fc2fans_club.py=================== # ====================fc2fans_club.py===================
if 'fc2' in filename: if 'fc2' in filename:
json_data = json.loads(fc2fans_club.main(file_number.strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-'))) 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: elif 'FC2' in filename:
json_data = json.loads(fc2fans_club.main(file_number.strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-'))) 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-')) #print(file_number.strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-'))
#=======================javbus.py======================= #=======================javbus.py=======================
else: else:
@ -156,6 +156,7 @@ def getNumberFromFilename(filepath):
os._exit(0) os._exit(0)
path = '' #设置path为全局变量，后面移动文件要用 path = '' #设置path为全局变量，后面移动文件要用
def creatFolder(): def creatFolder():
global actor
global path global path
if len(actor) > 240: #新建成功输出文件夹 if len(actor) > 240: #新建成功输出文件夹
path = 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 path = 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
@ -164,7 +165,13 @@ def creatFolder():
path = location_rule path = location_rule
#print(path) #print(path)
if not os.path.exists(path): if not os.path.exists(path):
os.makedirs(path) try:
os.makedirs(path)
except:
path = location_rule.replace(actor,"'其他'")
os.makedirs(path)
#=====================资源下载部分=========================== #=====================资源下载部分===========================
def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder! def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder!
config = ConfigParser() config = ConfigParser()

11
siro.py
View File

@ -6,9 +6,12 @@ from bs4 import BeautifulSoup
from ADC_function import * from ADC_function import *
def getTitle(a): def getTitle(a):
html = etree.fromstring(a, etree.HTMLParser()) try:
result = str(html.xpath('//*[@id="center_column"]/div[2]/h1/text()')).strip(" ['']") html = etree.fromstring(a, etree.HTMLParser())
return result.replace('/',',') result = str(html.xpath('//*[@id="center_column"]/div[2]/h1/text()')).strip(" ['']")
return result.replace('/', ',')
except:
return ''
def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text() 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() html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
result1=str(html.xpath('//th[contains(text(),"出演：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n') result1=str(html.xpath('//th[contains(text(),"出演：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
@ -96,4 +99,4 @@ def main(number2):
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 return js
#print(main('200GANA-1624')) #print(main('200GANA-1581'))