From 241ff00a0bdb3c8ec6fb2d1299e708aa1f3af796 Mon Sep 17 00:00:00 2001
From: mo_yy <54110819+moyy996@users.noreply.github.com>
Date: Tue, 21 Jan 2020 01:20:40 +0800
Subject: [PATCH] 2.1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
修复javdb抓取bug
---
ADC_function.py | 3 ++-
AV_Data_Capture.py | 31 ++++++++++++---------
README.md | 12 +++++++++
avsox.py | 8 +++---
config.ini | 5 ++--
core.py | 40 +++++++++++++++++++++------
fc2fans_club.py | 67 +++++++++++++++++++++++++++-------------------
javdb.py | 55 ++++++++++++-------------------------
siro.py | 2 ++
update_check.json | 4 +--
10 files changed, 132 insertions(+), 95 deletions(-)
diff --git a/ADC_function.py b/ADC_function.py
index d807061..0158bbf 100755
--- a/ADC_function.py
+++ b/ADC_function.py
@@ -10,7 +10,8 @@ import sys
from lxml import etree
import sys
import io
-sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
+# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
+# sys.setdefaultencoding('utf-8')
config_file='config.ini'
config = ConfigParser()
diff --git a/AV_Data_Capture.py b/AV_Data_Capture.py
index 40f194e..36088e0 100755
--- a/AV_Data_Capture.py
+++ b/AV_Data_Capture.py
@@ -5,7 +5,6 @@ import glob
import os
import time
import re
-import sys
from ADC_function import *
import json
import shutil
@@ -15,7 +14,7 @@ os.chdir(os.getcwd())
# ============global var===========
-version='1.9'
+version='2.1'
config = ConfigParser()
config.read(config_file, encoding='UTF-8')
@@ -44,10 +43,10 @@ def UpdateCheck():
html = json.loads(str(html2))
if not version == html['version']:
- print('[*] * New update ' + html['version'] + ' *')
- print('[*] * Download *')
+ print('[*] * New update ' + html['version'] + ' *')
+ print('[*] ↓ Download ↓')
print('[*] ' + html['download'])
- print('[*]=====================================')
+ print('[*]======================================================')
else:
print('[+]Update Check disabled!')
def movie_lists():
@@ -91,6 +90,8 @@ def getNumber(filepath):
filepath = filepath.replace("_", "-")
filepath.strip('22-sht.me').strip('-HD').strip('-hd')
filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath)) # 去除文件名中时间
+ if 'FC2' or 'fc2' in filename:
+ filename=filename.replace('-PPV','').replace('PPV-','')
try:
file_number = re.search('\w+-\d+', filename).group()
except: # 提取类似mkbd-s120番号
@@ -126,9 +127,9 @@ def RunCore():
os.system('python3 core.py' + ' "' + i + '" --number "' + getNumber(i) + '"') # 从py文件启动（用于源码py）
if __name__ =='__main__':
- print('[*]===========AV Data Capture===========')
- print('[*] Version '+version)
- print('[*]=====================================')
+ print('[*]================== AV Data Capture ===================')
+ print('[*] Version '+version)
+ print('[*]======================================================')
CreatFailedFolder()
UpdateCheck()
moveMovies()
@@ -137,6 +138,8 @@ if __name__ =='__main__':
count = 0
count_all = str(len(movie_lists()))
print('[+]Find',str(len(movie_lists())),'movies')
+ if config['common']['soft_link'] == '1':
+ print('[!] --- Soft link mode is ENABLE! ----')
for i in movie_lists(): #遍历电影列表 交给core处理
count = count + 1
percentage = str(count/int(count_all)*100)[:4]+'%'
@@ -144,14 +147,18 @@ if __name__ =='__main__':
try:
print("[!]Making Data for [" + i + "], the number is [" + getNumber(i) + "]")
RunCore()
- print("[*]=====================================")
+ print("[*]======================================================")
except: # 番号提取异常
print('[-]' + i + ' Cannot catch the number :')
- print('[-]Move ' + i + ' to failed folder')
- shutil.move(i, str(os.getcwd()) + '/' + 'failed/')
+ if config['common']['soft_link'] == '1':
+ print('[-]Link',i,'to failed folder')
+ os.symlink(i,str(os.getcwd()) + '/' + 'failed/')
+ else:
+ print('[-]Move ' + i + ' to failed folder')
+ shutil.move(i, str(os.getcwd()) + '/' + 'failed/')
continue
CEF(exclude_directory_1)
CEF(exclude_directory_2)
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和错误信息。")
\ No newline at end of file
+ input("[+][+]Press enter key exit, you can check the error messge before you exit.")
\ No newline at end of file
diff --git a/README.md b/README.md
index 431b822..4c4ff45 100644
--- a/README.md
+++ b/README.md
@@ -107,6 +107,14 @@ pip install pillow
设置成功输出目录和失败输出目录
+---
+#### 软链接
+>[common]
+>soft_link=0
+
+1为开启软链接模式
+0为关闭
+
---
### 网络设置
>[proxy]
@@ -225,6 +233,10 @@ pip install pillow
### 关于 ```Updata_check``` 和 ```JSON``` 相关的错误
跳转 [网络设置](#网络设置)
+---
+### 关于字幕文件移动功能
+字幕文件前缀必须与影片文件前缀一致，才可以使用该功能
+
---
### 关于```FileNotFoundError: [WinError 3] 系统找不到指定的路径。: 'JAV_output''```
在软件所在文件夹下新建 JAV_output 文件夹，可能是你没有把软件拉到和电影的同一目录
diff --git a/avsox.py b/avsox.py
index ee4c79c..16ab19d 100644
--- a/avsox.py
+++ b/avsox.py
@@ -71,16 +71,16 @@ def getTag(a): # 获取演员
return d
def main(number):
- a = get_html('https://avsox.asia/cn/search/' + number)
+ a = get_html('https://avsox.host/cn/search/' + number)
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
if result1 == '' or result1 == 'null' or result1 == 'None':
- a = get_html('https://avsox.asia/cn/search/' + number.replace('-', '_'))
+ a = get_html('https://avsox.host/cn/search/' + number.replace('-', '_'))
print(a)
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
if result1 == '' or result1 == 'null' or result1 == 'None':
- a = get_html('https://avsox.asia/cn/search/' + number.replace('_', ''))
+ a = get_html('https://avsox.host/cn/search/' + number.replace('_', ''))
print(a)
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
@@ -109,4 +109,4 @@ def main(number):
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
-#print(main('041516_541'))
\ No newline at end of file
+#print(main('012717_472'))
\ No newline at end of file
diff --git a/config.ini b/config.ini
index 5446524..6a735e8 100644
--- a/config.ini
+++ b/config.ini
@@ -2,9 +2,10 @@
main_mode=1
failed_output_folder=failed
success_output_folder=JAV_output
+soft_link=0
[proxy]
-proxy=127.0.0.1:1081
+proxy=
timeout=10
retry=3
@@ -17,7 +18,7 @@ update_check=1
[media]
media_warehouse=emby
-#emby or plex or kodi
+#emby or plex or kodi ,emby=jellyfin
[escape]
literals=\()
diff --git a/core.py b/core.py
index e534335..dc47a65 100755
--- a/core.py
+++ b/core.py
@@ -128,7 +128,7 @@ def getDataFromJSON(file_number): # 从JSON返回元数据
json_data = json.loads(javdb.main(file_number))
# ==
elif 'fc2' in file_number or 'FC2' in file_number:
- json_data = json.loads(fc2fans_club.main(file_number))
+ json_data = json.loads(fc2fans_club.main(file_number.replace('fc2-','').replace('fc2_','').replace('FC2-','').replace('fc2_','')))
# ==
elif 'HEYZO' in number or 'heyzo' in number or 'Heyzo' in number:
json_data = json.loads(avsox.main(file_number))
@@ -347,7 +347,7 @@ def PrintFiles():
for key, value in actor_photo.items():
print(" ", file=code)
print(" " + key + "", file=code)
- if not actor_photo == '': # or actor_photo == []:
+ if not value == '': # or actor_photo == []:
print(" " + value + "", file=code)
print(" ", file=code)
except:
@@ -394,7 +394,7 @@ def PrintFiles():
for key, value in actor_photo.items():
print(" ", file=code)
print(" " + key + "", file=code)
- if not actor_photo == '': # or actor_photo == []:
+ if not value == '': # or actor_photo == []:
print(" " + value + "", file=code)
print(" ", file=code)
except:
@@ -417,7 +417,7 @@ def PrintFiles():
if cn_sub == '1':
print(" 中文字幕", file=code)
print(" " + number + "", file=code)
- print(" " + release + "", file=code)
+ print(" " + release + "", file=code)
print(" " + cover + "", file=code)
print(" " + "https://www.javbus.com/" + number + "", file=code)
print("", file=code)
@@ -440,7 +440,7 @@ def PrintFiles():
for key, value in actor_photo.items():
print(" ", file=code)
print(" " + key + "", file=code)
- if not actor_photo == '': # or actor_photo == []:
+ if not value == '': # or actor_photo == []:
print(" " + value + "", file=code)
print(" ", file=code)
except:
@@ -538,7 +538,19 @@ def pasteFileToFolder(filepath, path): # 文件路径，番号，后缀，要
global houzhui
houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
try:
- os.rename(filepath, path + '/' + number + c_word + houzhui)
+ if config['common']['soft_link'] == '1': #如果soft_link=1 使用软链接
+ os.symlink(filepath, path + '/' + number + c_word + houzhui)
+ else:
+ os.rename(filepath, path + '/' + number + c_word + houzhui)
+ if os.path.exists(os.getcwd()+'/'+number + c_word + '.srt'): #字幕移动
+ os.rename(os.getcwd()+'/'+number + c_word + '.srt', path + '/' + number + c_word + '.srt')
+ print('[+]Sub moved!')
+ elif os.path.exists(os.getcwd()+'/'+number + c_word + '.ssa'):
+ os.rename(os.getcwd()+'/'+number + c_word + '.ssa', path + '/' + number + c_word + '.ssa')
+ print('[+]Sub moved!')
+ elif os.path.exists(os.getcwd()+'/'+number + c_word + '.sub'):
+ os.rename(os.getcwd()+'/'+number + c_word + '.sub', path + '/' + number + c_word + '.sub')
+ print('[+]Sub moved!')
except FileExistsError:
print('[-]File Exists! Please check your movie!')
print('[-]move to the root folder of the program.')
@@ -556,7 +568,19 @@ def pasteFileToFolder_mode2(filepath, path): # 文件路径，番号，后缀
houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
path = success_folder + '/' + location_rule
try:
- os.rename(filepath, path + '/' + number + part + c_word + houzhui)
+ if config['common']['soft_link'] == '1':
+ os.symlink(filepath, path + '/' + number + part + c_word + houzhui)
+ else:
+ os.rename(filepath, path + '/' + number + part + c_word + houzhui)
+ if os.path.exists(number+'.srt'): #字幕移动
+ os.rename(number + part + c_word + '.srt', path + '/' + number + part + c_word + '.srt')
+ print('[+]Sub moved!')
+ elif os.path.exists(number + part + c_word+'.ass'):
+ os.rename(number + part + c_word + '.ass', path + '/' + number + part + c_word + '.ass')
+ print('[+]Sub moved!')
+ elif os.path.exists(number + part + c_word+'.sub'):
+ os.rename(number + part + c_word + '.sub', path + '/' + number + part + c_word + '.sub')
+ print('[+]Sub moved!')
print('[!]Success')
except FileExistsError:
print('[-]File Exists! Please check your movie!')
@@ -598,7 +622,7 @@ def debug_mode():
continue
if i == 'actor_photo' or i == 'year':
continue
- print('[+] -', i, ':', v)
+ print('[+] -', i+str(9-len(i)*'-'), ':', v)
print('[+] ---Debug info---')
except:
aaa = ''
diff --git a/fc2fans_club.py b/fc2fans_club.py
index 747fa4c..72cb773 100755
--- a/fc2fans_club.py
+++ b/fc2fans_club.py
@@ -4,43 +4,50 @@ import json
import ADC_function
def getTitle(htmlcode): #获取厂商
+ #print(htmlcode)
html = etree.fromstring(htmlcode,etree.HTMLParser())
- result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/h2/text()')).strip(" ['']")
- return result
+ result = str(html.xpath('/html/body/div[2]/div/div[1]/h3/text()')).strip(" ['']")
+ result2 = str(re.sub('\D{2}2-\d+','',result)).replace(' ','',1)
+ #print(result2)
+ return result2
def getActor(htmlcode):
try:
html = etree.fromstring(htmlcode, etree.HTMLParser())
- result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[5]/a/text()')).strip(" ['']")
+ result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[5]/a/text()')).strip(" ['']")
return result
except:
return ''
def getStudio(htmlcode): #获取厂商
- try:
- html = etree.fromstring(htmlcode, etree.HTMLParser())
- result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[5]/a/text()')).strip(" ['']")
- return result
- except:
- return ''
+ html = etree.fromstring(htmlcode,etree.HTMLParser())
+ result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[3]/a[1]/text()')).strip(" ['']")
+ return result
def getNum(htmlcode): #获取番号
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
+ #print(result)
return result
def getRelease(htmlcode2): #
+ #a=ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
html=etree.fromstring(htmlcode2,etree.HTMLParser())
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']")
return result
-def getCover(htmlcode2): #获取厂商 #
+def getCover(htmlcode,number,htmlcode2): #获取厂商 #
+ #a = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id=' + str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-") + '&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
html = etree.fromstring(htmlcode2, etree.HTMLParser())
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[1]/a/img/@src')).strip(" ['']")
+ if result == '':
+ html = etree.fromstring(htmlcode, etree.HTMLParser())
+ result2 = str(html.xpath('//*[@id="slider"]/ul[1]/li[1]/img/@src')).strip(" ['']")
+ return 'https://fc2club.com' + result2
return 'http:' + result
def getOutline(htmlcode2): #获取番号 #
html = etree.fromstring(htmlcode2, etree.HTMLParser())
- result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',')
+ result = str(html.xpath('/html/body/div[1]/div[2]/div[2]/div[1]/div/article/section[4]/p/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',')
return result
def getTag(htmlcode): #获取番号
html = etree.fromstring(htmlcode, etree.HTMLParser())
- result = html.xpath('//*[@id="container"]/div[1]/div/article/section[6]/ul/li/a/text()')
- return result
+ result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[4]/a/text()'))
+ return result.strip(" ['']").replace("'",'').replace(' ','')
def getYear(release):
try:
result = re.search('\d{4}',release).group()
@@ -49,25 +56,29 @@ def getYear(release):
return ''
def main(number):
- number=number.replace('PPV','').replace('ppv','').strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-').strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-').replace('fc2ppv-','').replace('FC2PPV-','')
- htmlcode2 = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'')
- #htmlcode = ADC_function.get_html('http://fc2fans.club/html/FC2-' + number + '.html')
+ htmlcode2 = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+number+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
+ htmlcode = ADC_function.get_html('https://fc2club.com//html/FC2-' + number + '.html')
+ actor = getActor(htmlcode)
+ if getActor(htmlcode) == '':
+ actor = 'FC2系列'
dic = {
- 'title': getTitle(htmlcode2),
- 'studio': getStudio(htmlcode2),
- 'year': getYear(getRelease(htmlcode2)),
+ 'title': getTitle(htmlcode),
+ 'studio': getStudio(htmlcode),
+ 'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
'outline': getOutline(htmlcode2),
- 'runtime': getYear(getRelease(htmlcode2)),
- 'director': getStudio(htmlcode2),
- 'actor': getStudio(htmlcode2),
- 'release': getRelease(htmlcode2),
+ 'runtime': getYear(getRelease(htmlcode)),
+ 'director': getStudio(htmlcode),
+ 'actor': actor,
+ 'release': getRelease(number),
'number': 'FC2-'+number,
- 'cover': getCover(htmlcode2),
+ 'cover': getCover(htmlcode,number,htmlcode2),
'imagecut': 0,
- 'tag': getTag(htmlcode2),
+ 'tag': getTag(htmlcode),
'actor_photo':'',
- 'website': 'http://adult.contents.fc2.com/article_search.php?id=' + number,
- 'source': 'fc2fans_club.py',
+ 'website': 'https://fc2club.com//html/FC2-' + number + '.html',
+ 'source':'https://fc2club.com//html/FC2-' + number + '.html',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
- return js
\ No newline at end of file
+ return js
+
+#print(main('1051725'))
diff --git a/javdb.py b/javdb.py
index 34432f1..a85980c 100755
--- a/javdb.py
+++ b/javdb.py
@@ -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'))
diff --git a/siro.py b/siro.py
index bc4444a..c16537f 100755
--- a/siro.py
+++ b/siro.py
@@ -101,3 +101,5 @@ def main(number2):
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
+
+#print(main('SIRO-3607'))
\ No newline at end of file
diff --git a/update_check.json b/update_check.json
index d1870d5..08acd50 100644
--- a/update_check.json
+++ b/update_check.json
@@ -1,5 +1,5 @@
{
- "version": "1.9",
- "version_show":"1.9",
+ "version": "2.1",
+ "version_show":"2.1",
"download": "https://github.com/yoshiko2/AV_Data_Capture/releases"
}