bacow/AV_Data_Capture
1
0
Fork 0
Code Issues Pull Requests Actions 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
6 changed files with 75 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
siro.py
View File

@@ -3,70 +3,74 @@ from lxml import etree
import json
import requests
from bs4 import BeautifulSoup
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.")
from ADC_function import *
def getTitle(a):
html = etree.fromstring(a, etree.HTMLParser())
result = str(html.xpath('//*[@id="center_column"]/div[2]/h1/text()')).strip(" ['']")
return result
def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[1]/td/a/text()')).strip(" ['\\n ']")
return result
html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
result2=str(html.xpath('//table/tr[1]/td[1]/text()')).strip(" ['\\n ']")
result1 = str(html.xpath('//table/tr[1]/td[1]/a/text()')).strip(" ['\\n ']")
return str(result1+result2).strip('+')
def getStudio(a):
html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[2]/td/a/text()')).strip(" ['\\n ']")
return result
result2=str(html.xpath('//table[2]/tr[2]/td/text()')).strip(" ['\\n ']")
result1 = str(html.xpath('//table/tr[2]/td[1]/a/text()')).strip(" ['\\n ']")
return str(result1+result2).strip('+')
def getRuntime(a):
html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[3]/td/text()')).strip(" ['\\n ']")
return result
result2=str(html.xpath('//table/tr[3]/td[1]/text()')).strip(" ['\\n ']")
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):
html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[4]/td/text()')).strip(" ['\\n ']")
return result
result2=str(html.xpath('//table/tr[2]/td[4]/a/text()')).strip(" ['\\n ']")
result1 = str(html.xpath('//table/tr[2]/td[4]/text()')).strip(" ['\\n ']")
return str(result1 + result2).strip('+')
def getYear(a):
html = etree.fromstring(a, etree.HTMLParser())
#result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n ']")
result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n ']")
return result
result2=str(html.xpath('//table/tr[2]/td[5]/a/text()')).strip(" ['\\n ']")
result1=str(html.xpath('//table/tr[2]/td[5]/text()')).strip(" ['\\n ']")
return result2+result1
def getRelease(a):
html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n ']")
return result
result2=str(html.xpath('//table/tr[5]/td[1]/text()')).strip(" ['\\n ']")
result1 = str(html.xpath('//table/tr[5]/a/td[1]/text()')).strip(" ['\\n ']")
return str(result1 + result2).strip('+')
def getTag(a):
html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[9]/td/text()')).strip(" ['\\n ']")
return result
result2=str(html.xpath('//table/tr[8]/td[1]/a/text()')).strip(" ['\\n ']")
result1=str(html.xpath('//table/tr[8]/td[1]/text()')).strip(" ['\\n ']")
return str(result1 + result2).strip('+')
def getCover(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('//*[@id="center_column"]/div[2]/div[1]/div/div/h2/img/@src')).strip(" ['']")
return result
def getDirector(a):
html = etree.fromstring(a, etree.HTMLParser())
result = str(html.xpath('//table[2]/tr[7]/td/a/text()')).strip(" ['\\n ']")
return result
result1 = str(html.xpath('//table/tr[2]/td[1]/text()')).strip(" ['\\n ']")
result2 = str(html.xpath('//table/tr[2]/td[1]/a/text()')).strip(" ['\\n ']")
return str(result1 + result2).strip('+')
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):
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')
a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n ','')
#print(a)
dic = {
'title': getTitle(htmlcode).replace("\\n",'').replace(' ',''),
'studio': getStudio(a),
'year': getYear(a),
'year': str(re.search('\d{4}',getRelease(a)).group()),
'outline': getOutline(htmlcode),
'runtime': getRuntime(a),
'director': getDirector(a),
@@ -75,7 +79,10 @@ def main(number):
'number': number,
'cover': getCover(htmlcode),
'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')
return js
#print('https://www.mgstage.com/product/product_detail/'+str(number))
return js
#print(main('SIRO-3552'))