diff --git a/AV_Data_Capture.py b/AV_Data_Capture.py
index 42b8ba1..98de9c6 100644
--- a/AV_Data_Capture.py
+++ b/AV_Data_Capture.py
@@ -6,7 +6,7 @@ import sys
from ADC_function import *
import json
-version='0.10.5'
+version='0.10.6'
def UpdateCheck():
html2 = get_html('https://raw.githubusercontent.com/wenead99/AV_Data_Capture/master/update_check.json')
@@ -78,4 +78,4 @@ if __name__ =='__main__':
print("[!]Cleaning empty folders")
CEF('JAV_output')
print("[+]All finished!!!")
- input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看错误信息。")
+ input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看错误信息。")
\ No newline at end of file
diff --git a/core.py b/core.py
index 27a0e44..9801d9d 100644
--- a/core.py
+++ b/core.py
@@ -55,6 +55,7 @@ def getNumberFromFilename(filepath):
global cover
global imagecut
global tag
+ global image_main
global naming_rule
global location_rule
@@ -122,19 +123,19 @@ def getNumberFromFilename(filepath):
- 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_list= str(json_data['actor']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表
- release = json_data['release']
- number = json_data['number']
- cover = json_data['cover']
- imagecut = json_data['imagecut']
- tag = str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表
- actor = str(actor_list).strip("[ ]").replace("'",'').replace(" ",'')
+ 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_list = str(json_data['actor']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表
+ release = json_data['release']
+ number = json_data['number']
+ cover = json_data['cover']
+ imagecut = json_data['imagecut']
+ tag = str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表
+ actor = str(actor_list).strip("[ ]").replace("'",'').replace(" ",'')
#====================处理异常字符====================== #\/:*?"<>|
#if "\\" in title or "/" in title or ":" in title or "*" in title or "?" in title or '"' in title or '<' in title or ">" in title or "|" in title or len(title) > 200:
diff --git a/siro.py b/siro.py
index aad875e..3692bdd 100644
--- a/siro.py
+++ b/siro.py
@@ -8,81 +8,92 @@ 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
+ return result.replace('/',',')
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()
- 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('+')
+ result1=str(html.xpath('//th[contains(text(),"出演：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
+ result2=str(html.xpath('//th[contains(text(),"出演：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
+ return str(result1+result2).strip('+').replace("', '",'').replace('"','').replace('/',',')
def getStudio(a):
- html = etree.fromstring(a, etree.HTMLParser())
- 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('+')
+ html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
+ result1=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
+ result2=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
+ return str(result1+result2).strip('+').replace("', '",'').replace('"','')
def getRuntime(a):
- html = etree.fromstring(a, etree.HTMLParser())
- 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')
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n')
+ result2 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n')
+ return str(result1 + result2).strip('+').rstrip('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('+')
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
+ '\\n')
+ result2 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
+ '\\n')
+ return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
def getNum(a):
- html = etree.fromstring(a, etree.HTMLParser())
- 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 ']")
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//th[contains(text(),"品番：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
+ '\\n')
+ result2 = str(html.xpath('//th[contains(text(),"品番：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
+ '\\n')
return str(result1 + result2).strip('+')
-def getYear(a):
- html = etree.fromstring(a, etree.HTMLParser())
- 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 getYear(getRelease):
+ try:
+ result = str(re.search('\d{4}',getRelease).group())
+ return result
+ except:
+ return getRelease
def getRelease(a):
- html = etree.fromstring(a, etree.HTMLParser())
- 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 ']")
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
+ '\\n')
+ result2 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
+ '\\n')
return str(result1 + result2).strip('+')
def getTag(a):
- html = etree.fromstring(a, etree.HTMLParser())
- 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('+')
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
+ '\\n')
+ result2 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
+ '\\n')
+ return str(result1 + result2).strip('+').replace("', '\\n",",").replace("', '","").replace('"','')
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())
- 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('+')
+ html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
+ result1 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip(
+ '\\n')
+ result2 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
+ '\\n')
+ return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
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),cookies={'adc':'1'})
+def main(number2):
+ number=number2.upper()
+ 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)
+ a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n ','').replace(' ','').replace('\n ','').replace('\n ','')
dic = {
'title': getTitle(htmlcode).replace("\\n",'').replace(' ',''),
'studio': getStudio(a),
- 'year': str(re.search('\d{4}',getRelease(a)).group()),
'outline': getOutline(htmlcode),
'runtime': getRuntime(a),
'director': getDirector(a),
'actor': getActor(a),
'release': getRelease(a),
- 'number': number,
+ 'number': getNum(a),
'cover': getCover(htmlcode),
'imagecut': 0,
- 'tag': getTag(a).replace("'\\n',",'').replace(' ', '').replace("\\n','\\n",','),
- 'label':getLabel(a)
+ 'tag': getTag(a),
+ 'label':getLabel(a),
+ 'year': getYear(getRelease(a)), # str(re.search('\d{4}',getRelease(a)).group()),
}
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
-#print(main('SIRO-3552'))
\ No newline at end of file
+
+#print(main('200GANA-1624'))
\ No newline at end of file