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

Beta 10.2 Update

Browse Source
This commit is contained in:
wenead99 2019-06-19 18:19:34 +08:00 committed by GitHub
parent 36c436772c
commit 764fba74ec
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 75 additions and 60 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
ADC_function.py
View File

@ -1,8 +1,15 @@
import requests import requests
from configparser import ConfigParser from configparser import RawConfigParser
import os import os
import re
config = ConfigParser() # content = open('proxy.ini').read()
# content = re.sub(r"\xfe\xff","", content)
# content = re.sub(r"\xff\xfe","", content)
# content = re.sub(r"\xef\xbb\xbf","", content)
# open('BaseConfig.cfg', 'w').write(content)
config = RawConfigParser()
if os.path.exists('proxy.ini'): if os.path.exists('proxy.ini'):
config.read('proxy.ini', encoding='UTF-8') config.read('proxy.ini', encoding='UTF-8')
else: else:
@ -10,14 +17,14 @@ else:
print("[proxy]",file=code) print("[proxy]",file=code)
print("proxy=127.0.0.1:1080",file=code) print("proxy=127.0.0.1:1080",file=code)
def get_html(url):#网页请求核心 def get_html(url,cookies = None):#网页请求核心
if not str(config['proxy']['proxy']) == '': if not str(config['proxy']['proxy']) == '':
proxies = { proxies = {
"http" : "http://" + str(config['proxy']['proxy']), "http" : "http://" + str(config['proxy']['proxy']),
"https": "https://" + 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'} 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) getweb = requests.get(str(url), headers=headers, proxies=proxies,cookies=cookies)
getweb.encoding = 'utf-8' getweb.encoding = 'utf-8'
# print(getweb.text) # print(getweb.text)
try: try:
@ -27,7 +34,7 @@ def get_html(url):#网页请求核心
else: else:
headers = { 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'} '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) getweb = requests.get(str(url), headers=headers,cookies=cookies)
getweb.encoding = 'utf-8' getweb.encoding = 'utf-8'
try: try:
return getweb.text return getweb.text

4
AV_Data_Capture.py
View File

@ -19,8 +19,10 @@ def movie_lists():
f2 = glob.glob(os.getcwd() + r"\*.mkv") f2 = glob.glob(os.getcwd() + r"\*.mkv")
# FLV # FLV
g2 = glob.glob(os.getcwd() + r"\*.flv") g2 = glob.glob(os.getcwd() + r"\*.flv")
# TS
h2 = glob.glob(os.getcwd() + r"\*.ts")
total = a2+b2+c2+d2+e2+f2+g2 total = a2+b2+c2+d2+e2+f2+g2+h2
return total return total
def lists_from_test(custom_nuber): #电影列表 def lists_from_test(custom_nuber): #电影列表

2
core.py
View File

@ -299,7 +299,7 @@ def cutImage():
h = img.height h = img.height
img.save(path + '/' + naming_rule + '.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 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)$', filepath).group()) houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
os.rename(filepath, naming_rule + houzhui) os.rename(filepath, naming_rule + houzhui)
shutil.move(naming_rule + houzhui, path) shutil.move(naming_rule + houzhui, path)

4
fc2fans_club.py
View File

@ -38,8 +38,8 @@ def getOutline(htmlcode,number): #获取番号
# 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()')).replace("\\n",'',10000).strip(" ['']").replace("'",'',10000)
# return result # return result
def main(number): def main(number2):
str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-") number=number2.replace('PPV','').replace('ppv','')
htmlcode = ADC_function.get_html('http://fc2fans.club/html/FC2-' + number + '.html') htmlcode = ADC_function.get_html('http://fc2fans.club/html/FC2-' + number + '.html')
dic = { dic = {
'title': getTitle(htmlcode), 'title': getTitle(htmlcode),

35
javbus.py
View File

@ -9,14 +9,7 @@ from bs4 import BeautifulSoup#need install
from PIL import Image#need install from PIL import Image#need install
import time import time
import json import json
from ADC_function import *
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=10,headers=headers).text
try:
return getweb
except:
print("[-]Connect Failed! Please check your Proxy.")
def getTitle(htmlcode): #获取标题 def getTitle(htmlcode): #获取标题
doc = pq(htmlcode) doc = pq(htmlcode)
@ -34,7 +27,6 @@ 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'))
def getRelease(htmlcode): #获取出版日期 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(" ['']")
@ -62,8 +54,10 @@ 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
def getSerise(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[7]/a/text()')).strip(" ['']")
return result
def getTag(htmlcode): # 获取演员 def getTag(htmlcode): # 获取演员
tag = [] tag = []
soup = BeautifulSoup(htmlcode, 'lxml') soup = BeautifulSoup(htmlcode, 'lxml')
@ -79,7 +73,7 @@ def main(number):
htmlcode=get_html('https://www.javbus.com/'+number) htmlcode=get_html('https://www.javbus.com/'+number)
dww_htmlcode=get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", '')) dww_htmlcode=get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
dic = { dic = {
'title': getTitle(htmlcode), 'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))),
'studio': getStudio(htmlcode), 'studio': getStudio(htmlcode),
'year': str(re.search('\d{4}',getYear(htmlcode)).group()), 'year': str(re.search('\d{4}',getYear(htmlcode)).group()),
'outline': getOutline(dww_htmlcode), 'outline': getOutline(dww_htmlcode),
@ -90,7 +84,8 @@ def main(number):
'number': getNum(htmlcode), 'number': getNum(htmlcode),
'cover': getCover(htmlcode), 'cover': getCover(htmlcode),
'imagecut': 1, 'imagecut': 1,
'tag': getTag(htmlcode) 'tag': getTag(htmlcode),
'label': getSerise(htmlcode),
} }
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')
@ -98,7 +93,7 @@ def main(number):
htmlcode = get_html('https://www.javbus.com/' + number) htmlcode = get_html('https://www.javbus.com/' + number)
dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", '')) dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
dic = { dic = {
'title': getTitle(htmlcode), 'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))),
'studio': getStudio(htmlcode), 'studio': getStudio(htmlcode),
'year': getYear(htmlcode), 'year': getYear(htmlcode),
'outline': getOutline(dww_htmlcode), 'outline': getOutline(dww_htmlcode),
@ -109,7 +104,8 @@ def main(number):
'number': getNum(htmlcode), 'number': getNum(htmlcode),
'cover': getCover(htmlcode), 'cover': getCover(htmlcode),
'imagecut': 1, 'imagecut': 1,
'tag': getTag(htmlcode) 'tag': getTag(htmlcode),
'label': getSerise(htmlcode),
} }
js2 = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8') js2 = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js2 return js2
@ -118,11 +114,12 @@ def main(number):
def main_uncensored(number): def main_uncensored(number):
htmlcode = get_html('https://www.javbus.com/' + 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 = { dic = {
'title': getTitle(htmlcode), 'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))),
'studio': getStudio(htmlcode), 'studio': getStudio(htmlcode),
'year': getYear(htmlcode), 'year': getYear(htmlcode),
'outline': getOutline(htmlcode), 'outline': getOutline(dww_htmlcode),
'runtime': getRuntime(htmlcode), 'runtime': getRuntime(htmlcode),
'director': getDirector(htmlcode), 'director': getDirector(htmlcode),
'actor': getActor(htmlcode), 'actor': getActor(htmlcode),
@ -130,6 +127,7 @@ def main_uncensored(number):
'number': getNum(htmlcode), 'number': getNum(htmlcode),
'cover': getCover(htmlcode), 'cover': getCover(htmlcode),
'tag': getTag(htmlcode), 'tag': getTag(htmlcode),
'label': getSerise(htmlcode),
'imagecut': 0, 'imagecut': 0,
} }
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')
@ -138,7 +136,7 @@ def main_uncensored(number):
number2 = number.replace('-', '_') number2 = number.replace('-', '_')
htmlcode = get_html('https://www.javbus.com/' + number2) htmlcode = get_html('https://www.javbus.com/' + number2)
dic2 = { dic2 = {
'title': getTitle(htmlcode), 'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))),
'studio': getStudio(htmlcode), 'studio': getStudio(htmlcode),
'year': getYear(htmlcode), 'year': getYear(htmlcode),
'outline': '', 'outline': '',
@ -149,6 +147,7 @@ def main_uncensored(number):
'number': getNum(htmlcode), 'number': getNum(htmlcode),
'cover': getCover(htmlcode), 'cover': getCover(htmlcode),
'tag': getTag(htmlcode), 'tag': getTag(htmlcode),
'label':getSerise(htmlcode),
'imagecut': 0, 'imagecut': 0,
} }
js2 = json.dumps(dic2, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8') js2 = json.dumps(dic2, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')

69
siro.py
View File

@ -3,70 +3,74 @@ from lxml import etree
import json import json
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from ADC_function import *
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'}
cookies = {'adc':'1'}
getweb = requests.get(str(url),timeout=10,cookies=cookies,headers=headers).text
try:
return getweb
except:
print("[-]Connect Failed! Please check your Proxy.")
def getTitle(a): def getTitle(a):
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
result = str(html.xpath('//*[@id="center_column"]/div[2]/h1/text()')).strip(" ['']") result = str(html.xpath('//*[@id="center_column"]/div[2]/h1/text()')).strip(" ['']")
return result return result
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()) html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
result=str(html.xpath('//table[2]/tr[1]/td/a/text()')).strip(" ['\\n ']") result2=str(html.xpath('//table/tr[1]/td[1]/text()')).strip(" ['\\n ']")
return result result1 = str(html.xpath('//table/tr[1]/td[1]/a/text()')).strip(" ['\\n ']")
return str(result1+result2).strip('+')
def getStudio(a): def getStudio(a):
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[2]/td/a/text()')).strip(" ['\\n ']") result2=str(html.xpath('//table[2]/tr[2]/td/text()')).strip(" ['\\n ']")
return result result1 = str(html.xpath('//table/tr[2]/td[1]/a/text()')).strip(" ['\\n ']")
return str(result1+result2).strip('+')
def getRuntime(a): def getRuntime(a):
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[3]/td/text()')).strip(" ['\\n ']") result2=str(html.xpath('//table/tr[3]/td[1]/text()')).strip(" ['\\n ']")
return result result1 = str(html.xpath('//table/tr[3]/td[1]/a/text()')).strip(" ['\\n ']")
return str(result1 + result2).strip('+').strip('mi')
def getLabel(a):
html = etree.fromstring(a, etree.HTMLParser())
result2=str(html.xpath('//table/tr[6]/td[1]/text()')).strip(" ['\\n ']")
result1 = str(html.xpath('//table/tr[6]/td[1]/a/text()')).strip(" ['\\n ']")
return str(result1 + result2).strip('+')
def getNum(a): def getNum(a):
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[4]/td/text()')).strip(" ['\\n ']") result2=str(html.xpath('//table/tr[2]/td[4]/a/text()')).strip(" ['\\n ']")
return result result1 = str(html.xpath('//table/tr[2]/td[4]/text()')).strip(" ['\\n ']")
return str(result1 + result2).strip('+')
def getYear(a): def getYear(a):
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
#result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n ']") result2=str(html.xpath('//table/tr[2]/td[5]/a/text()')).strip(" ['\\n ']")
result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n ']") result1=str(html.xpath('//table/tr[2]/td[5]/text()')).strip(" ['\\n ']")
return result return result2+result1
def getRelease(a): def getRelease(a):
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n ']") result2=str(html.xpath('//table/tr[5]/td[1]/text()')).strip(" ['\\n ']")
return result result1 = str(html.xpath('//table/tr[5]/a/td[1]/text()')).strip(" ['\\n ']")
return str(result1 + result2).strip('+')
def getTag(a): def getTag(a):
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[9]/td/text()')).strip(" ['\\n ']") result2=str(html.xpath('//table/tr[8]/td[1]/a/text()')).strip(" ['\\n ']")
return result result1=str(html.xpath('//table/tr[8]/td[1]/text()')).strip(" ['\\n ']")
return str(result1 + result2).strip('+')
def getCover(htmlcode): def getCover(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser()) html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('//*[@id="center_column"]/div[2]/div[1]/div/div/h2/img/@src')).strip(" ['']") result = str(html.xpath('//*[@id="center_column"]/div[2]/div[1]/div/div/h2/img/@src')).strip(" ['']")
return result return result
def getDirector(a): def getDirector(a):
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
result = str(html.xpath('//table[2]/tr[7]/td/a/text()')).strip(" ['\\n ']") result1 = str(html.xpath('//table/tr[2]/td[1]/text()')).strip(" ['\\n ']")
return result result2 = str(html.xpath('//table/tr[2]/td[1]/a/text()')).strip(" ['\\n ']")
return str(result1 + result2).strip('+')
def getOutline(htmlcode): def getOutline(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser()) html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']") result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
return result return result
def main(number): def main(number):
htmlcode=get_html('https://www.mgstage.com/product/product_detail/'+str(number)) htmlcode=get_html('https://www.mgstage.com/product/product_detail/'+str(number),cookies={'adc':'1'})
soup = BeautifulSoup(htmlcode, 'lxml') soup = BeautifulSoup(htmlcode, 'lxml')
a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n ','') a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n ','')
#print(a)
dic = { dic = {
'title': getTitle(htmlcode).replace("\\n",'').replace(' ',''), 'title': getTitle(htmlcode).replace("\\n",'').replace(' ',''),
'studio': getStudio(a), 'studio': getStudio(a),
'year': getYear(a), 'year': str(re.search('\d{4}',getRelease(a)).group()),
'outline': getOutline(htmlcode), 'outline': getOutline(htmlcode),
'runtime': getRuntime(a), 'runtime': getRuntime(a),
'director': getDirector(a), 'director': getDirector(a),
@ -75,7 +79,10 @@ def main(number):
'number': number, 'number': number,
'cover': getCover(htmlcode), 'cover': getCover(htmlcode),
'imagecut': 0, 'imagecut': 0,
'tag':' ', 'tag': getTag(a).replace("'\\n',",'').replace(' ', '').replace("\\n','\\n",','),
'label':getLabel(a)
} }
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')
#print('https://www.mgstage.com/product/product_detail/'+str(number))
return js return js
#print(main('SIRO-3552'))