Skip to content

Commit

Permalink
0.5更新
Browse files Browse the repository at this point in the history
  • Loading branch information
@mvdctop
mvdctop authored Jun 1, 2019
1 parent 79679ad commit 2dc2da4
Show file tree
Hide file tree
Showing 7 changed files with 388 additions and 114 deletions.
10 changes: 10 additions & 0 deletions ADC_function.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
import requests

def get_html(url):#网页请求核心
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),timeout=5,headers=headers)
getweb.encoding='utf-8'
try:
return getweb.text
except:
print("[-]Connect Failed! Please check your Proxy.")
8 changes: 4 additions & 4 deletions AV_Data_Capture.py
View file
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import glob
import os
import time
import re

def movie_lists():
#MP4
Expand Down Expand Up @@ -47,14 +48,13 @@ def rreplace(self, old, new, *max):
os.chdir(os.getcwd())
for i in movie_lists(): #遍历电影列表 交给core处理
if '_' in i:
os.rename(i, rreplace(i,'_','-',1))
i = rreplace(i,'_','-',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)
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）
print("[*]=====================================")

print("[!]Cleaning empty folders")
CEF('JAV_output')
print("[+]All finished!!!")
time.sleep(3)

time.sleep(3)
225 changes: 115 additions & 110 deletions core.py
View file
Original file line number Diff line number Diff line change
@@ -1,68 +1,27 @@
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
from PIL import Image
import time
import javbus
import json
import fc2fans_club
import siro

#=====================爬虫核心部分==========================
def get_html(url):#网页请求核心
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),timeout=5,headers=headers).text
try:
return getweb
except:
print("[-]Connect Failed! Please check your Proxy.")
#初始化全局变量
title=''
studio=''
year=''
outline=''
runtime=''
director=''
actor=''
release=''
number=''
cover=''
imagecut=''

def getTitle(htmlcode): #获取标题
doc = pq(htmlcode)
title=str(doc('div.container h3').text()).replace(' ','-')
return title
def getStudio(htmlcode): #获取厂商
html = etree.fromstring(htmlcode,etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
return result
def getYear(htmlcode): #获取年份
html = etree.fromstring(htmlcode,etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
result2 = str(re.search('\d{4}', result).group(0))
return result2
def getCover(htmlcode): #获取封面链接
doc = pq(htmlcode)
image = doc('a.bigImage')
return image.attr('href')
print(image.attr('href'))
def getRelease(htmlcode): #获取出版日期
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
return result
def getRuntime(htmlcode): #获取分钟
soup = BeautifulSoup(htmlcode, 'lxml')
a = soup.find(text=re.compile('分鐘'))
return a
def getActor(htmlcode): #获取女优
b=[]
soup=BeautifulSoup(htmlcode,'lxml')
a=soup.find_all(attrs={'class':'star-name'})
for i in a:
b.append(i.text)
return ",".join(b)
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(" ['']")
return result
def getDirector(htmlcode): #获取导演
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']")
return result
def getOutline(htmlcode): #获取演员
doc = pq(htmlcode)
result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text())
return result
#=====================资源下载部分===========================
def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder!
import requests
Expand All @@ -81,36 +40,36 @@ def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in
print("[-]Download Failed2!")
time.sleep(3)
os._exit(0)
def PrintFiles(html,path,number):
def PrintFiles(path):
try:
if not os.path.exists(path):
os.makedirs(path)
with open(path + "/" + getNum(html) + ".nfo", "wt", encoding='UTF-8') as code:
with open(path + "/" + number + ".nfo", "wt", encoding='UTF-8') as code:
print("<movie>", file=code)
print(" <title>" + getTitle(html) + "</title>", file=code)
print(" <title>" + title + "</title>", file=code)
print(" <set>", file=code)
print(" </set>", file=code)
print(" <studio>" + getStudio(html) + "+</studio>", file=code)
print(" <year>" + getYear(html) + "</year>", file=code)
print(" <outline>"+getOutline(get_html_dww(number))+"</outline>", file=code)
print(" <plot>"+getOutline(get_html_dww(number))+"</plot>", file=code)
print(" <runtime>"+str(getRuntime(html)).replace(" ","")+"</runtime>", file=code)
print(" <director>" + getDirector(html) + "</director>", file=code)
print(" <poster>" + getNum(html) + ".png</poster>", file=code)
print(" <thumb>" + getNum(html) + ".png</thumb>", file=code)
print(" <fanart>"+getNum(html) + '.jpg'+"</fanart>", file=code)
print(" <studio>" + studio + "+</studio>", file=code)
print(" <year>" + year + "</year>", file=code)
print(" <outline>"+outline+"</outline>", file=code)
print(" <plot>"+outline+"</plot>", file=code)
print(" <runtime>"+str(runtime).replace(" ","")+"</runtime>", file=code)
print(" <director>" + director + "</director>", file=code)
print(" <poster>" + number + ".png</poster>", file=code)
print(" <thumb>" + number + ".png</thumb>", file=code)
print(" <fanart>"+number + '.jpg'+"</fanart>", file=code)
print(" <actor>", file=code)
print(" <name>" + getActor(html) + "</name>", file=code)
print(" <name>" + actor + "</name>", file=code)
print(" </actor>", file=code)
print(" <maker>" + getStudio(html) + "</maker>", file=code)
print(" <maker>" + studio + "</maker>", file=code)
print(" <label>", file=code)
print(" </label>", file=code)
print(" <num>" + getNum(html) + "</num>", file=code)
print(" <release>" + getRelease(html) + "</release>", file=code)
print(" <cover>"+getCover(html)+"</cover>", file=code)
print(" <website>" + "https://www.javbus.com/"+getNum(html) + "</website>", file=code)
print(" <num>" + number + "</num>", file=code)
print(" <release>" + release + "</release>", file=code)
print(" <cover>"+cover+"</cover>", file=code)
print(" <website>" + "https://www.javbus.com/"+number + "</website>", file=code)
print("</movie>", file=code)
print("[+]Writeed! "+path + "/" + getNum(html) + ".nfo")
print("[+]Writeed! "+path + "/" + number + ".nfo")
except IOError as e:
print("[-]Write Failed!")
print(e)
Expand All @@ -119,25 +78,67 @@ def PrintFiles(html,path,number):
print("[-]Write Failed!")

#=====================本地文件处理===========================


def argparse_get_file():
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("file", help="Write the file path on here")
args = parser.parse_args()
return args.file
def getNumberFromFilename(filepath):
global title
global studio
global year
global outline
global runtime
global director
global actor
global release
global number
global cover
global imagecut

filename = str(os.path.basename(filepath)) #电影文件名
str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filename))

print("[!]Making Data for ["+filename+"]")
a = str(re.search('\w+-\w+', filename).group())
#print(a)

# =======================网站规则添加==============================
try:
a = str(re.search('\w+-\w+', filename).group())
return a
try:
if re.search('^\d{5,}', a).group() in filename:
json_data = json.loads(javbus.main_uncensored(a.replace("-", "_")))
except:
if 'fc2' in filename:
json_data = json.loads(fc2fans_club.main(a))
elif 'FC2' in filename:
json_data = json.loads(fc2fans_club.main(a))
elif 'siro' in filename:
json_data = json.loads(siro.main(a))
elif 'SIRO' in filename:
json_data = json.loads(siro.main(a))
elif '259luxu' in filename:
json_data = json.loads(siro.main(a))
elif '259LUXU' in filename:
json_data = json.loads(siro.main(a))
else:
json_data = json.loads(javbus.main(a))
# ====================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 = json_data['actor']
release = json_data['release']
number = json_data['number']
cover = json_data['cover']
imagecut = json_data['imagecut']
except:
print('[-]File '+filename+'`s number can not be caught')
print('[-]Move ' + filename + 'to failed folder')
print('[-]Move ' + filename + ' to failed folder')
if not os.path.exists('failed/'): # 新建failed文件夹
os.makedirs('failed/')
if not os.path.exists('failed/'):
Expand All @@ -146,52 +147,56 @@ def getNumberFromFilename(filepath):
os._exit(0)
shutil.move(filepath, str(os.getcwd())+'/'+'failed/')
os._exit(0)
def get_html_javbus(number):
return get_html("https://www.javbus.com/" + str(number))
def get_html_dww(number):
return get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))

path = '' #设置path为全局变量，后面移动文件要用
def creatFolder(html,number):

def creatFolder():
global path
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)")
os._exit(0)
if len(getActor(html)) > 240: #新建成功输出文件夹
if len(actor) > 240: #新建成功输出文件夹
path = 'JAV_output' + '/' + '超多人' + '/' + number #path为影片+元数据所在目录
else:
path = 'JAV_output' + '/' + getActor(html) + '/' + number
path = 'JAV_output' + '/' + str(actor) + '/' + str(number)
if not os.path.exists(path):
os.makedirs(path)
path = str(os.getcwd())+'/'+path
def imageDownload(htmlcode,filepath,number): #封面是否下载成功，否则移动到failed
if DownloadFileWithFilename(getCover(htmlcode),number + '.jpg', path) == 'failed':
def imageDownload(filepath): #封面是否下载成功，否则移动到failed
if DownloadFileWithFilename(cover,str(number) + '.jpg', path) == 'failed':
shutil.move(filepath, 'failed/')
os._exit(0)
DownloadFileWithFilename(getCover(htmlcode), number + '.jpg', path)
DownloadFileWithFilename(cover, number + '.jpg', path)
print('[+]Image Downloaded!', path +'/'+number+'.jpg')
def cutImage(number):
try:
def cutImage():
if imagecut == 1:
try:
img = Image.open(path + '/' + number + '.jpg')
imgSize = img.size
w = img.width
h = img.height
img2 = img.crop((w / 1.9, 0, w, h))
img2.save(path + '/' + number + '.png')
except:
print('[-]Cover cut failed!')
else:
img = Image.open(path + '/' + number + '.jpg')
imgSize=img.size
w=img.width
h=img.height
img2 = img.crop((w/1.9, 0, w, h))
img2.save(path + '/' + number + '.png')
except:
print('[-]Cover cut failed!')
def pasteFileToFolder(filepath, number, path): #文件路径，番号，后缀，要移动至的位置
w = img.width
h = img.height
img.save(path + '/' + number + '.png')

def pasteFileToFolder(filepath, path): #文件路径，番号，后缀，要移动至的位置
houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|avi|rmvb|wmv|mov|mp4|mkv|flv)$', filepath).group())
os.rename(filepath, number + houzhui)
shutil.move(number + houzhui, path)

if __name__ == '__main__':
filepath=argparse_get_file() #影片的路径
number=getNumberFromFilename(filepath) #定义番号
htmlcode=get_html_javbus(number) #获取的HTML代码
creatFolder(htmlcode,number) #创建文件夹
imageDownload(htmlcode,filepath,number) #creatFoder会返回番号路径
PrintFiles(htmlcode, path,number)#打印文件
cutImage(number) #裁剪图
pasteFileToFolder(filepath,number,path) #移动文件
getNumberFromFilename(filepath) #定义番号
creatFolder() #创建文件夹
imageDownload(filepath) #creatFoder会返回番号路径
PrintFiles(path)#打印文件
cutImage() #裁剪图
pasteFileToFolder(filepath,path) #移动文件
52 changes: 52 additions & 0 deletions fc2fans_club.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
import re
from lxml import etree#need install
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(" ['']")
return result
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
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(" ['']")
return result
def getRelease(number):
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(a,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): #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')
html = etree.fromstring(a, etree.HTMLParser())
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[1]/a/img/@src')).strip(" ['']")
return 'http:'+result
def getOutline(htmlcode,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(a, etree.HTMLParser())
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).replace("\\n",'',10000).strip(" ['']").replace("'",'',10000)
return result

def main(number):
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': getRelease(number),
'outline': getOutline(htmlcode,number),
'runtime': '',
'director': getStudio(htmlcode),
'actor': '',
'release': getRelease(number),
'number': number,
'cover': getCover(htmlcode,number),
'imagecut': 0,
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
return js
Loading

0 comments on commit 2dc2da4

Please sign in to comment.