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

2.1

Browse Source 
修复javdb抓取bug
This commit is contained in:
mo_yy
2020-01-21 01:20:40 +08:00
parent c073a1e253
commit 241ff00a0b
10 changed files with 132 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
javdb.py
View File

@@ -4,7 +4,6 @@ import json
from bs4 import BeautifulSoup
from ADC_function import *
def getTitle(a):
try:
html = etree.fromstring(a, etree.HTMLParser())
@@ -12,98 +11,75 @@ def getTitle(a):
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()
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(),"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(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').rstrip('mi')
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('"', '')
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(result2 + result1).strip('+')
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()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+')
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('"', '')
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:
@@ -115,7 +91,7 @@ def main(number):
'actor': getActor(b),
'title': getTitle(b).replace("\\n", '').replace(' ', '').replace(getActor(a), '').replace(getNum(a),
'').replace(
'无码', '').replace('有码', '').lstrip(' ').replace(number, ''),
'无码', '').replace('有码', '').lstrip(' ').replace(number,''),
'studio': getStudio(b),
'outline': getOutline(b),
'runtime': getRuntime(b),
@@ -128,7 +104,7 @@ def main(number):
'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',
}
@@ -141,13 +117,14 @@ def main(number):
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 = 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(' ').replace(number, ''),
'无码', '').replace('有码', '').lstrip(' ').replace(number,''),
'studio': getStudio(b),
'outline': getOutline(b),
'runtime': getRuntime(b),
@@ -160,7 +137,7 @@ def main(number):
'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',
}
@@ -170,4 +147,6 @@ def main(number):
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
# 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'))