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

0.3 Beta 更好的代码风格，便于阅读

Browse Source
This commit is contained in:
wenead99 2019-05-28 19:47:22 +08:00 committed by GitHub
parent abcf1a49e7
commit bda0c5becd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 72 additions and 78 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

126
core.py
View File

@ -9,7 +9,8 @@ from bs4 import BeautifulSoup#need install
from PIL import Image#need install from PIL import Image#need install
import time import time
def get_html(url): #=====================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'} 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),proxies={"http": "http://127.0.0.1:2334","https": "https://127.0.0.1:2334"},timeout=5,headers=headers).text getweb = requests.get(str(url),proxies={"http": "http://127.0.0.1:2334","https": "https://127.0.0.1:2334"},timeout=5,headers=headers).text
try: try:
@ -18,65 +19,64 @@ def get_html(url):
print(e) print(e)
except IOError as e1: except IOError as e1:
print(e1) print(e1)
#================================================
def getTitle(htmlcode): def getTitle(htmlcode): #获取标题
doc = pq(htmlcode) doc = pq(htmlcode)
title=str(doc('div.container h3').text()).replace(' ','-') title=str(doc('div.container h3').text()).replace(' ','-')
return title return title
def getStudio(htmlcode): def getStudio(htmlcode): #获取厂商
html = etree.fromstring(htmlcode,etree.HTMLParser()) html = etree.fromstring(htmlcode,etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']") result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
return result return result
def getYear(htmlcode): def getYear(htmlcode): #获取年份
html = etree.fromstring(htmlcode,etree.HTMLParser()) html = etree.fromstring(htmlcode,etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']") 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)) result2 = str(re.search('\d{4}', result).group(0))
return result2 return result2
def getCover(htmlcode): def getCover(htmlcode): #获取封面链接
doc = pq(htmlcode) doc = pq(htmlcode)
image = doc('a.bigImage') image = doc('a.bigImage')
return image.attr('href') return image.attr('href')
print(image.attr('href')) print(image.attr('href'))
def getRelease(htmlcode): def getRelease(htmlcode): #获取出版日期
html = etree.fromstring(htmlcode, etree.HTMLParser()) html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']") result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
return result return result
def getRuntime(htmlcode): def getRuntime(htmlcode): #获取分钟
soup = BeautifulSoup(htmlcode, 'lxml') soup = BeautifulSoup(htmlcode, 'lxml')
a = soup.find(text=re.compile('分鐘')) a = soup.find(text=re.compile('分鐘'))
return a return a
def getActor(htmlcode): def getActor(htmlcode): #获取女优
b=[] b=[]
soup=BeautifulSoup(htmlcode,'lxml') soup=BeautifulSoup(htmlcode,'lxml')
a=soup.find_all(attrs={'class':'star-name'}) a=soup.find_all(attrs={'class':'star-name'})
for i in a: for i in a:
b.append(i.text) b.append(i.text)
return ",".join(b) return ",".join(b)
def getNum(htmlcode): def getNum(htmlcode): #获取番号
html = etree.fromstring(htmlcode, etree.HTMLParser()) html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']") result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
return result return result
def getDirector(htmlcode): def getDirector(htmlcode): #获取导演
html = etree.fromstring(htmlcode, etree.HTMLParser()) html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']") result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']")
return result return result
def getOutline(htmlcode): def getOutline(htmlcode): #获取演员
doc = pq(htmlcode) doc = pq(htmlcode)
result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text()) result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text())
return result return result
#================================================ #=====================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!
import requests import requests
import re
try: try:
if not os.path.exists(path): if not os.path.exists(path):
os.makedirs(path) os.makedirs(path)
r = requests.get(url) r = requests.get(url)
with open(str(path) + "/"+str(filename), "wb") as code: with open(str(path) + "/"+str(filename), "wb") as code:
code.write(r.content) code.write(r.content)
# print('[+]Downloaded!',str(path) + "/"+str(filename))
except IOError as e: except IOError as e:
print("[-]Download Failed1!") print("[-]Download Failed1!")
print("[-]Error:"+str(e))
print("[-]Movie not found in Javbus.com!") print("[-]Movie not found in Javbus.com!")
print("[*]=====================================") print("[*]=====================================")
return "failed" return "failed"
@ -85,8 +85,7 @@ def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in
print("[-]Download Failed2!") print("[-]Download Failed2!")
time.sleep(3) time.sleep(3)
os._exit(0) os._exit(0)
def PrintFiles(html,html_outline,path):
def PrintFiles(path):
try: try:
if not os.path.exists(path): if not os.path.exists(path):
os.makedirs(path) os.makedirs(path)
@ -122,81 +121,76 @@ def PrintFiles(path):
except Exception as e1: except Exception as e1:
print(e1) print(e1)
print("[-]Write Failed!") print("[-]Write Failed!")
#================================================
if __name__ == '__main__':
#命令行处理 #=====================本地文件处理===========================
def argparse_get_file():
import argparse import argparse
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument("file", help="Write the file path on here") parser.add_argument("file", help="Write the file path on here")
args = parser.parse_args() args = parser.parse_args()
#=============================== return args.file
#获取文件名称 def getNumberFromFilename(filepath):
filename=str(os.path.basename(args.file)) #\[\d{4}(\-|\/|.)\d{1,2}\1\d{1,2}\] filename = str(os.path.basename(filepath)) #电影文件名
#去除文件名中日期 str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filename))
deldate=str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ","",filename))
#检测是否可以获取番号，如果不行终止本程序
def number_getter():
print("[!]Making Data for ["+filename+"]") print("[!]Making Data for ["+filename+"]")
try: try:
a = str(re.search('\w+-\w+', deldate).group()) a = str(re.search('\w+-\w+', filename).group())
return a return a
except: except:
print('[-]File '+filename+'`s number can not be caught') print('[-]File '+filename+'`s number can not be caught')
print('[-]Move ' + filename + 'to failed folder') print('[-]Move ' + filename + 'to failed folder')
filepath = str(args).replace("Namespace(file='", '').replace("')", '').replace('\\\\', '\\')
if not os.path.exists('failed/'): # 新建failed文件夹 if not os.path.exists('failed/'): # 新建failed文件夹
os.makedirs('failed/') os.makedirs('failed/')
if not os.path.exists('failed/'): if not os.path.exists('failed/'):
print("[-]failed!Dirs can not be make (Please run as Administrator)") print("[-]failed!Dirs can not be make (Please run as Administrator)")
time.sleep(3) time.sleep(3)
os._exit(0) os._exit(0)
shutil.move(filepath, str(os.getcwd())+'/failed/') shutil.move(filepath, str(os.getcwd())+'/'+'failed/')
os._exit(0) os._exit(0)
number=number_getter() def get_html_javbus(number):
#print(number) return get_html("https://www.javbus.com/" + str(number))
#获取网页HTML def get_html_dww(number):
html = get_html("https://www.javbus.com/"+str(number)) return get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
html_outline=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
#处理超长文件夹名称 def creatFolder(html,number):
if len(getActor(html)) > 240: global path
path = 'JAV_output' + '/' + '超多人' + '/' + getNum(html) #path为影片+元数据所在目录 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
path = 'JAV_output' + '/' + '超多人' + '/' + number #path为影片+元数据所在目录
else: else:
path = 'JAV_output' + '/' + getActor(html) + '/' + getNum(html) path = 'JAV_output' + '/' + getActor(html) + '/' + number
if not os.path.exists(path): if not os.path.exists(path):
os.makedirs(path) os.makedirs(path)
#文件路径处理 path = str(os.getcwd())+'/'+path
filepath = str(args).replace("Namespace(file='",'').replace("')",'').replace('\\\\', '\\') def imageDownload(htmlcode,filepath,number): #封面是否下载成功，否则移动到failed
houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|avi|rmvb|wmv|mov|mp4|mkv|flv)$',filepath).group()) if DownloadFileWithFilename(getCover(htmlcode),number + '.jpg', path) == 'failed':
#下载元数据
#如果DownloadFileWithFilename返回为failed，就退出本程序
if not os.path.exists('failed/'): #新建failed文件夹
os.makedirs('failed/')
if not os.path.exists('failed/'):
print("[-]failed!Dirs can not be make (Please run as Administrator)")
os._exit(0)
if DownloadFileWithFilename(getCover(html), getNum(html) + '.jpg', path) == 'failed':
shutil.move(filepath, 'failed/')
time.sleep(3)
os._exit(0)
else:
if DownloadFileWithFilename(getCover(html), getNum(html) + '.jpg', path) == 'failed':
shutil.move(filepath, 'failed/') shutil.move(filepath, 'failed/')
os._exit(0) os._exit(0)
DownloadFileWithFilename(getCover(html), getNum(html) + '.jpg', path) DownloadFileWithFilename(getCover(htmlcode), number + '.jpg', path)
print('[+]Downloaded!', path +'/'+getNum(html)+'.jpg') print('[+]Downloaded!', path +'/'+number+'.jpg')
#切割图片做封面 def cutImage(number):
try: try:
img = Image.open(path + '/' + getNum(html) + '.jpg') img = Image.open(path + '/' + number + '.jpg')
img2 = img.crop((421, 0, 800, 538)) img2 = img.crop((421, 0, 800, 538))
img2.save(path + '/' + getNum(html) + '.png') img2.save(path + '/' + number + '.png')
except: except:
print('[-]Cover cut failed!') print('[-]Cover cut failed!')
# 电源文件位置处理 def pasteFileToFolder(filepath, number, path): #文件路径，番号，后缀，要移动至的位置
houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|avi|rmvb|wmv|mov|mp4|mkv|flv)$', filepath).group())
os.rename(filepath, number + houzhui) os.rename(filepath, number + houzhui)
shutil.move(number + houzhui, path) shutil.move(number + houzhui, path)
#下载元数据
PrintFiles(path) if __name__ == '__main__':
print('[!]Finished!') filepath=argparse_get_file() #影片的路径
time.sleep(3) 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
cutImage(number) #裁剪图片
pasteFileToFolder(filepath,number,path) #移动文件