Update 3.7-5 DEBUG ONLY
This commit is contained in:
root
@@ -2,6 +2,8 @@ import re
|
||||
from lxml import etree
|
||||
import json
|
||||
from bs4 import BeautifulSoup
|
||||
import sys
|
||||
sys.path.append('../')
|
||||
from ADC_function import *
|
||||
# import sys
|
||||
# import io
|
||||
@@ -24,7 +26,10 @@ def getTitle(a):
|
||||
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()) # //table/tr[1]/td[1]/text()
|
||||
result1 = html.xpath('//th[contains(text(),"声優")]/../td/a/text()')
|
||||
try:
|
||||
result1 = html.xpath('//th[contains(text(),"声优")]/../td/a/text()')
|
||||
except:
|
||||
result1 = ''
|
||||
return result1
|
||||
def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
|
||||
a = actor.split(',')
|
||||
@@ -35,7 +40,13 @@ def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
|
||||
return d
|
||||
def getStudio(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result = html.xpath('//th[contains(text(),"ブランド名")]/../td/span[1]/a/text()')[0]
|
||||
try:
|
||||
try:
|
||||
result = html.xpath('//th[contains(text(),"系列名")]/../td/span[1]/a/text()')[0]
|
||||
except:
|
||||
result = html.xpath('//th[contains(text(),"社团名")]/../td/span[1]/a/text()')[0]
|
||||
except:
|
||||
result = ''
|
||||
return result
|
||||
def getRuntime(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
@@ -44,7 +55,13 @@ def getRuntime(a):
|
||||
return str(result1 + result2).strip('+').rstrip('mi')
|
||||
def getLabel(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result = html.xpath('//th[contains(text(),"ブランド名")]/../td/span[1]/a/text()')[0]
|
||||
try:
|
||||
try:
|
||||
result = html.xpath('//th[contains(text(),"系列名")]/../td/span[1]/a/text()')[0]
|
||||
except:
|
||||
result = html.xpath('//th[contains(text(),"社团名")]/../td/span[1]/a/text()')[0]
|
||||
except:
|
||||
result = ''
|
||||
return result
|
||||
def getYear(getRelease):
|
||||
try:
|
||||
@@ -54,12 +71,12 @@ def getYear(getRelease):
|
||||
return getRelease
|
||||
def getRelease(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = html.xpath('//th[contains(text(),"販売日")]/../td/a/text()')[0]
|
||||
result1 = html.xpath('//th[contains(text(),"贩卖日")]/../td/a/text()')[0]
|
||||
return result1.replace('年','-').replace('月','-').replace('日','')
|
||||
def getTag(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
try:
|
||||
result = html.xpath('//th[contains(text(),"ジャンル")]/../td/div/a/text()')
|
||||
result = html.xpath('//th[contains(text(),"分类")]/../td/div/a/text()')
|
||||
return result
|
||||
except:
|
||||
return ''
|
||||
@@ -85,7 +102,10 @@ def getCover(htmlcode):
|
||||
return result
|
||||
def getDirector(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result = html.xpath('//th[contains(text(),"シナリオ")]/../td/a/text()')[0]
|
||||
try:
|
||||
result = html.xpath('//th[contains(text(),"剧情")]/../td/a/text()')[0]
|
||||
except:
|
||||
result = ''
|
||||
return result
|
||||
def getOutline(htmlcode):
|
||||
html = etree.fromstring(htmlcode, etree.HTMLParser())
|
||||
@@ -96,36 +116,52 @@ def getOutline(htmlcode):
|
||||
return str(total).strip(" ['']").replace("', '', '",r'\n').replace("', '",r'\n').strip(", '', '")
|
||||
def getSeries(a):
|
||||
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
|
||||
result1 = html.xpath('//th[contains(text(),"声優")]/../td/a/text()')
|
||||
return result1
|
||||
try:
|
||||
try:
|
||||
result = html.xpath('//th[contains(text(),"系列名")]/../td/span[1]/a/text()')[0]
|
||||
except:
|
||||
result = html.xpath('//th[contains(text(),"社团名")]/../td/span[1]/a/text()')[0]
|
||||
except:
|
||||
result = ''
|
||||
return result
|
||||
def main(number):
|
||||
number = number.upper()
|
||||
htmlcode = get_html('https://www.dlsite.com/pro/work/=/product_id/' + number + '.html')
|
||||
try:
|
||||
number = number.upper()
|
||||
htmlcode = get_html('https://www.dlsite.com/pro/work/=/product_id/' + number + '.html',
|
||||
cookies={'locale': 'zh-cn'})
|
||||
|
||||
dic = {
|
||||
'actor': getActor(htmlcode),
|
||||
'title': getTitle(htmlcode),
|
||||
'studio': getStudio(htmlcode),
|
||||
'outline': getOutline(htmlcode),
|
||||
'runtime': getRuntime(htmlcode),
|
||||
'director': getDirector(htmlcode),
|
||||
'release': getRelease(htmlcode),
|
||||
'number': number,
|
||||
'cover': 'https:' + getCover(htmlcode),
|
||||
'cover_small': '',
|
||||
'imagecut': 0,
|
||||
'tag': getTag(htmlcode),
|
||||
'label': getLabel(htmlcode),
|
||||
'year': getYear(getRelease(htmlcode)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': '',
|
||||
'website': 'https://www.dlsite.com/pro/work/=/product_id/' + number + '.html',
|
||||
'source': 'dlsite.py',
|
||||
'series': getSeries(htmlcode),
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
dic = {
|
||||
'actor': getActor(htmlcode),
|
||||
'title': getTitle(htmlcode),
|
||||
'studio': getStudio(htmlcode),
|
||||
'outline': getOutline(htmlcode),
|
||||
'runtime': '',
|
||||
'director': getDirector(htmlcode),
|
||||
'release': getRelease(htmlcode),
|
||||
'number': number,
|
||||
'cover': 'https:' + getCover(htmlcode),
|
||||
'cover_small': '',
|
||||
'imagecut': 0,
|
||||
'tag': getTag(htmlcode),
|
||||
'label': getLabel(htmlcode),
|
||||
'year': getYear(getRelease(htmlcode)), # str(re.search('\d{4}',getRelease(a)).group()),
|
||||
'actor_photo': '',
|
||||
'website': 'https://www.dlsite.com/pro/work/=/product_id/' + number + '.html',
|
||||
'source': 'dlsite.py',
|
||||
'series': getSeries(htmlcode),
|
||||
}
|
||||
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
|
||||
return js
|
||||
except:
|
||||
data = {
|
||||
"title": "",
|
||||
}
|
||||
js = json.dumps(
|
||||
data, ensure_ascii=False, sort_keys=True, indent=4, separators=(",", ":")
|
||||
)
|
||||
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。")
|
||||
if __name__ == "__main__":
|
||||
print(main('VJ013479'))
|
||||
print(main('VJ013178'))
|
||||
|
||||
Reference in New Issue
Block a user