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

Merge pull request #77 from moyy996/master

Browse Source 
Update 2.2
This commit is contained in:
Yoshiko 2020-01-21 14:20:13 +08:00 committed by GitHub
commit 0b5d68732f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 57 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
config.ini
View File

@ -5,7 +5,7 @@ success_output_folder=JAV_output
soft_link=0
[proxy]
proxy=127.0.0.1:1081
proxy=
timeout=10
retry=3

9
core.py
View File

@ -140,7 +140,7 @@ def getDataFromJSON(file_number): # 从JSON返回元数据
json_data = json.loads(javbus.main(file_number))
if getDataState(json_data) == 0: # 如果元数据获取失败，请求番号至其他网站抓取
json_data = json.loads(avsox.main(file_number))
elif getDataState(json_data) == 0: # 如果元数据获取失败，请求番号至其他网站抓取
if getDataState(json_data) == 0: # 如果元数据获取失败，请求番号至其他网站抓取
json_data = json.loads(javdb.main(file_number))
# ================================================网站规则添加结束================================================
@ -183,6 +183,7 @@ def getDataFromJSON(file_number): # 从JSON返回元数据
title = title.replace('<', '')
title = title.replace('>', '')
title = title.replace('|', '')
release = release.replace('/', '-')
tmpArr = cover_small.split(',')
if len(tmpArr) > 0:
cover_small = tmpArr[0].strip('\"').strip('\'')
@ -346,7 +347,7 @@ def PrintFiles():
for key, value in actor_photo.items():
print(" <actor>", file=code)
print(" <name>" + key + "</name>", file=code)
if not actor_photo == '': # or actor_photo == []:
if not value == '': # or actor_photo == []:
print(" <thumb>" + value + "</thumb>", file=code)
print(" </actor>", file=code)
except:
@ -393,7 +394,7 @@ def PrintFiles():
for key, value in actor_photo.items():
print(" <actor>", file=code)
print(" <name>" + key + "</name>", file=code)
if not actor_photo == '': # or actor_photo == []:
if not value == '': # or actor_photo == []:
print(" <thumb>" + value + "</thumb>", file=code)
print(" </actor>", file=code)
except:
@ -439,7 +440,7 @@ def PrintFiles():
for key, value in actor_photo.items():
print(" <actor>", file=code)
print(" <name>" + key + "</name>", file=code)
if not actor_photo == '': # or actor_photo == []:
if not value == '': # or actor_photo == []:
print(" <thumb>" + value + "</thumb>", file=code)
print(" </actor>", file=code)
except:

77
javdb.py
View File

@ -8,19 +8,26 @@ def getTitle(a):
try:
html = etree.fromstring(a, etree.HTMLParser())
result = str(html.xpath('/html/body/section/div/h2/strong/text()')).strip(" ['']")
return re.sub('.*\] ','',result.replace('/', ',').replace('\\xa0','').replace(' : ',''))
return re.sub('.*\] ', '', result.replace('/', ',').replace('\\xa0', '').replace(' : ', ''))
except:
return re.sub('.*\] ','',result.replace('/', ',').replace('\\xa0',''))
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()
return re.sub('.*\] ', '', result.replace('/', ',').replace('\\xa0', ''))
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()
result1 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace(",\\xa0","").replace("'","").replace(' ','').replace(',,','').lstrip(',').replace(',',', ')
return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',').replace(',', ', ')
def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
a = actor.split(',')
d={}
for i in a:
p={i:''}
d.update(p)
return d
def getStudio(a):
html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"製作")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"製作")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1+result2).strip('+').replace("', '",'').replace('"','')
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
def getRuntime(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/text()')).strip(" ['']")
@ -30,15 +37,15 @@ def getLabel(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
def getNum(a):
html = etree.fromstring(a, etree.HTMLParser())
result1 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+')
return str(result2 + result1).strip('+')
def getYear(getRelease):
try:
result = str(re.search('\d{4}',getRelease).group())
result = str(re.search('\d{4}', getRelease).group())
return result
except:
return getRelease
@ -51,33 +58,40 @@ def getTag(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace(",\\xa0","").replace("'","").replace(' ','').replace(',,','').lstrip(',')
return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',')
def getCover_small(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result = 'http:' + html.xpath(
'//div[@id=\'videos\']/div[@class=\'grid columns\']/div[@class=\'grid-item column\'][1]/a['
'@class=\'box\']/div[@class=\'item-image fix-scale-cover\']/img/@src')[0]
return result
def getCover(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/section/div/div[2]/div[1]/a/img/@src')).strip(" ['']")
if result == '':
result = str(html.xpath('/html/body/section/div/div[3]/div[1]/a/img/@src')).strip(" ['']")
result = str(html.xpath('/html/body/section/div/div[4]/div[1]/a/img/@src')).strip(" ['']")
return result
def getDirector(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
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):
number = number.upper()
try:
a = get_html('https://javdb.com/search?q=' + number + '&f=all').replace(u'\xa0', u' ')
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
result1 = html.xpath('//*[@id="videos"]/div/div/a/@href')[0]
b = get_html('https://javdb.com' + result1).replace(u'\xa0', u' ')
dic = {
'actor': getActor(a),
'actor': getActor(b),
'title': getTitle(b).replace("\\n", '').replace(' ', '').replace(getActor(a), '').replace(getNum(a),
'').replace(
'无码', '').replace('有码', '').lstrip(' '),
'无码', '').replace('有码', '').lstrip(' ').replace(number,''),
'studio': getStudio(b),
'outline': getOutline(b),
'runtime': getRuntime(b),
@ -85,27 +99,32 @@ def main(number):
'release': getRelease(b),
'number': getNum(b),
'cover': getCover(b),
'imagecut': 0,
'cover_small': getCover_small(a),
'imagecut': 3,
'tag': getTag(b),
'label': getLabel(b),
'year': getYear(getRelease(b)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': '',
'actor_photo': getActorPhoto(getActor(b)),
'website': 'https://javdb.com' + result1,
'source': 'javdb.py',
}
if getNum(b) != number: # 与搜索到的番号不匹配
dic['title'] = ''
dic['number'] = ''
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
except:
a = get_html('https://javdb.com/search?q=' + number + '&f=all').replace(u'\xa0', u' ')
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
result1 = html.xpath('//*[@id="videos"]/div/div/a/@href')[0]
print(html.xpath('//*[@id="videos"]/div/div/a/@href'))
b = get_html('https://javdb.com' + result1).replace(u'\xa0', u' ')
dic = {
'actor': getActor(b),
'title': getTitle(b).replace("\\n", '').replace(' ', '').replace(getActor(a), '').replace(
getNum(b),
'').replace(
'无码', '').replace('有码', '').lstrip(' '),
'无码', '').replace('有码', '').lstrip(' ').replace(number,''),
'studio': getStudio(b),
'outline': getOutline(b),
'runtime': getRuntime(b),
@ -113,15 +132,21 @@ def main(number):
'release': getRelease(b),
'number': getNum(b),
'cover': getCover(b),
'imagecut': 0,
'cover_small': getCover_small(a),
'imagecut': 3,
'tag': getTag(b),
'label': getLabel(b),
'year': getYear(getRelease(b)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': '',
'actor_photo': getActorPhoto(getActor(b)),
'website': 'https://javdb.com' + result1,
'source': 'javdb.py',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,separators=(',', ':'), ) # .encode('UTF-8')
if getNum(b) != number: # 与搜索到的番号不匹配
dic['title'] = ''
dic['number'] = ''
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
#print(get_html('https://javdb1.com/v/WwZ0Q'))
# main('DV-1562')
# 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和错误信息。")
# print(get_html('https://javdb1.com/v/WwZ0Q'))