tanpengsccd/AV_Data_Capture
1
0
Fork 0
Code Issues Pull Requests 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
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ADC_function.py
View File

@ -10,7 +10,8 @@ import sys
from lxml import etree from lxml import etree
import sys import sys
import io 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_file='config.ini'
config = ConfigParser() config = ConfigParser()

23
AV_Data_Capture.py
View File

@ -5,7 +5,6 @@ import glob
import os import os
import time import time
import re import re
import sys
from ADC_function import * from ADC_function import *
import json import json
import shutil import shutil
@ -15,7 +14,7 @@ os.chdir(os.getcwd())
# ============global var=========== # ============global var===========
version='1.9' version='2.1'
config = ConfigParser() config = ConfigParser()
config.read(config_file, encoding='UTF-8') config.read(config_file, encoding='UTF-8')
@ -45,9 +44,9 @@ def UpdateCheck():
if not version == html['version']: if not version == html['version']:
print('[*] * New update ' + html['version'] + ' *') print('[*] * New update ' + html['version'] + ' *')
print('[*] * Download *') print('[*] ↓ Download ↓')
print('[*] ' + html['download']) print('[*] ' + html['download'])
print('[*]=====================================') print('[*]======================================================')
else: else:
print('[+]Update Check disabled!') print('[+]Update Check disabled!')
def movie_lists(): def movie_lists():
@ -91,6 +90,8 @@ def getNumber(filepath):
filepath = filepath.replace("_", "-") filepath = filepath.replace("_", "-")
filepath.strip('22-sht.me').strip('-HD').strip('-hd') 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 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: try:
file_number = re.search('\w+-\d+', filename).group() file_number = re.search('\w+-\d+', filename).group()
except: # 提取类似mkbd-s120番号 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） os.system('python3 core.py' + ' "' + i + '" --number "' + getNumber(i) + '"') # 从py文件启动（用于源码py）
if __name__ =='__main__': if __name__ =='__main__':
print('[*]===========AV Data Capture===========') print('[*]================== AV Data Capture ===================')
print('[*] Version '+version) print('[*] Version '+version)
print('[*]=====================================') print('[*]======================================================')
CreatFailedFolder() CreatFailedFolder()
UpdateCheck() UpdateCheck()
moveMovies() moveMovies()
@ -137,6 +138,8 @@ if __name__ =='__main__':
count = 0 count = 0
count_all = str(len(movie_lists())) count_all = str(len(movie_lists()))
print('[+]Find',str(len(movie_lists())),'movies') 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 for i in movie_lists(): #遍历电影列表 交给core处理
count = count + 1 count = count + 1
percentage = str(count/int(count_all)*100)[:4]+'%' percentage = str(count/int(count_all)*100)[:4]+'%'
@ -144,9 +147,13 @@ if __name__ =='__main__':
try: try:
print("[!]Making Data for [" + i + "], the number is [" + getNumber(i) + "]") print("[!]Making Data for [" + i + "], the number is [" + getNumber(i) + "]")
RunCore() RunCore()
print("[*]=====================================") print("[*]======================================================")
except: # 番号提取异常 except: # 番号提取异常
print('[-]' + i + ' Cannot catch the number :') print('[-]' + i + ' Cannot catch the number :')
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') print('[-]Move ' + i + ' to failed folder')
shutil.move(i, str(os.getcwd()) + '/' + 'failed/') shutil.move(i, str(os.getcwd()) + '/' + 'failed/')
continue continue
@ -154,4 +161,4 @@ if __name__ =='__main__':
CEF(exclude_directory_1) CEF(exclude_directory_1)
CEF(exclude_directory_2) CEF(exclude_directory_2)
print("[+]All finished!!!") 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。") input("[+][+]Press enter key exit, you can check the error messge before you exit.")

12
README.md
View File

@ -107,6 +107,14 @@ pip install pillow
设置成功输出目录和失败输出目录 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 ### 网络设置
>[proxy] >[proxy]
@ -225,6 +233,10 @@ pip install pillow
### 关于 ```Updata_check``` 和 ```JSON``` 相关的错误 ### 关于 ```Updata_check``` 和 ```JSON``` 相关的错误
跳转 [网络设置](#网络设置) 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''``` ### 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 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

8
avsox.py
View File

@ -71,16 +71,16 @@ def getTag(a): # 获取演员
return d return d
def main(number): 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() html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']") result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
if result1 == '' or result1 == 'null' or result1 == 'None': 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) print(a)
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']") result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
if result1 == '' or result1 == 'null' or result1 == 'None': 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) print(a)
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']") 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') js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js return js
#print(main('041516_541')) #print(main('012717_472'))

5
config.ini
View File

@ -2,9 +2,10 @@
main_mode=1 main_mode=1
failed_output_folder=failed failed_output_folder=failed
success_output_folder=JAV_output success_output_folder=JAV_output
soft_link=0
[proxy] [proxy]
proxy=127.0.0.1:1081 proxy=
timeout=10 timeout=10
retry=3 retry=3
@ -17,7 +18,7 @@ update_check=1
[media] [media]
media_warehouse=emby media_warehouse=emby
#emby or plex or kodi #emby or plex or kodi ,emby=jellyfin
[escape] [escape]
literals=\() literals=\()

36
core.py
View File

@ -128,7 +128,7 @@ def getDataFromJSON(file_number): # 从JSON返回元数据
json_data = json.loads(javdb.main(file_number)) json_data = json.loads(javdb.main(file_number))
# == # ==
elif 'fc2' in file_number or 'FC2' in 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: elif 'HEYZO' in number or 'heyzo' in number or 'Heyzo' in number:
json_data = json.loads(avsox.main(file_number)) json_data = json.loads(avsox.main(file_number))
@ -347,7 +347,7 @@ def PrintFiles():
for key, value in actor_photo.items(): for key, value in actor_photo.items():
print(" <actor>", file=code) print(" <actor>", file=code)
print(" <name>" + key + "</name>", 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(" <thumb>" + value + "</thumb>", file=code)
print(" </actor>", file=code) print(" </actor>", file=code)
except: except:
@ -394,7 +394,7 @@ def PrintFiles():
for key, value in actor_photo.items(): for key, value in actor_photo.items():
print(" <actor>", file=code) print(" <actor>", file=code)
print(" <name>" + key + "</name>", 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(" <thumb>" + value + "</thumb>", file=code)
print(" </actor>", file=code) print(" </actor>", file=code)
except: except:
@ -417,7 +417,7 @@ def PrintFiles():
if cn_sub == '1': if cn_sub == '1':
print(" <genre>中文字幕</genre>", file=code) print(" <genre>中文字幕</genre>", file=code)
print(" <num>" + number + "</num>", file=code) print(" <num>" + number + "</num>", file=code)
print(" <release>" + release + "</release>", file=code) print(" <premiered>" + release + "</premiered>", file=code)
print(" <cover>" + cover + "</cover>", file=code) print(" <cover>" + cover + "</cover>", file=code)
print(" <website>" + "https://www.javbus.com/" + number + "</website>", file=code) print(" <website>" + "https://www.javbus.com/" + number + "</website>", file=code)
print("</movie>", file=code) print("</movie>", file=code)
@ -440,7 +440,7 @@ def PrintFiles():
for key, value in actor_photo.items(): for key, value in actor_photo.items():
print(" <actor>", file=code) print(" <actor>", file=code)
print(" <name>" + key + "</name>", 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(" <thumb>" + value + "</thumb>", file=code)
print(" </actor>", file=code) print(" </actor>", file=code)
except: except:
@ -538,7 +538,19 @@ def pasteFileToFolder(filepath, path): # 文件路径，番号，后缀，要
global houzhui global houzhui
houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group()) houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
try: try:
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) 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: except FileExistsError:
print('[-]File Exists! Please check your movie!') print('[-]File Exists! Please check your movie!')
print('[-]move to the root folder of the program.') 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)$', filepath).group()) houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
path = success_folder + '/' + location_rule path = success_folder + '/' + location_rule
try: try:
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) 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') print('[!]Success')
except FileExistsError: except FileExistsError:
print('[-]File Exists! Please check your movie!') print('[-]File Exists! Please check your movie!')
@ -598,7 +622,7 @@ def debug_mode():
continue continue
if i == 'actor_photo' or i == 'year': if i == 'actor_photo' or i == 'year':
continue continue
print('[+] -', i, ':', v) print('[+] -', i+str(9-len(i)*'-'), ':', v)
print('[+] ---Debug info---') print('[+] ---Debug info---')
except: except:
aaa = '' aaa = ''

61
fc2fans_club.py
View File

@ -4,43 +4,50 @@ import json
import ADC_function import ADC_function
def getTitle(htmlcode): #获取厂商 def getTitle(htmlcode): #获取厂商
#print(htmlcode)
html = etree.fromstring(htmlcode,etree.HTMLParser()) html = etree.fromstring(htmlcode,etree.HTMLParser())
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/h2/text()')).strip(" ['']") result = str(html.xpath('/html/body/div[2]/div/div[1]/h3/text()')).strip(" ['']")
return result result2 = str(re.sub('\D{2}2-\d+','',result)).replace(' ','',1)
#print(result2)
return result2
def getActor(htmlcode): def getActor(htmlcode):
try: try:
html = etree.fromstring(htmlcode, etree.HTMLParser()) 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 return result
except: except:
return '' return ''
def getStudio(htmlcode): #获取厂商 def getStudio(htmlcode): #获取厂商
try:
html = etree.fromstring(htmlcode,etree.HTMLParser()) 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[3]/a[1]/text()')).strip(" ['']")
return result return result
except:
return ''
def getNum(htmlcode): #获取番号 def getNum(htmlcode): #获取番号
html = etree.fromstring(htmlcode, etree.HTMLParser()) html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']") result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
#print(result)
return result return result
def getRelease(htmlcode2): # 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()) 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(" ['']") result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']")
return result 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()) 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(" ['']") 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 return 'http:' + result
def getOutline(htmlcode2): #获取番号 # def getOutline(htmlcode2): #获取番号 #
html = etree.fromstring(htmlcode2, etree.HTMLParser()) 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 return result
def getTag(htmlcode): #获取番号 def getTag(htmlcode): #获取番号
html = etree.fromstring(htmlcode, etree.HTMLParser()) html = etree.fromstring(htmlcode, etree.HTMLParser())
result = html.xpath('//*[@id="container"]/div[1]/div/article/section[6]/ul/li/a/text()') result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[4]/a/text()'))
return result return result.strip(" ['']").replace("'",'').replace(' ','')
def getYear(release): def getYear(release):
try: try:
result = re.search('\d{4}',release).group() result = re.search('\d{4}',release).group()
@ -49,25 +56,29 @@ def getYear(release):
return '' return ''
def main(number): 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='+number+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
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('https://fc2club.com//html/FC2-' + number + '.html')
#htmlcode = ADC_function.get_html('http://fc2fans.club/html/FC2-' + number + '.html') actor = getActor(htmlcode)
if getActor(htmlcode) == '':
actor = 'FC2系列'
dic = { dic = {
'title': getTitle(htmlcode2), 'title': getTitle(htmlcode),
'studio': getStudio(htmlcode2), 'studio': getStudio(htmlcode),
'year': getYear(getRelease(htmlcode2)), 'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
'outline': getOutline(htmlcode2), 'outline': getOutline(htmlcode2),
'runtime': getYear(getRelease(htmlcode2)), 'runtime': getYear(getRelease(htmlcode)),
'director': getStudio(htmlcode2), 'director': getStudio(htmlcode),
'actor': getStudio(htmlcode2), 'actor': actor,
'release': getRelease(htmlcode2), 'release': getRelease(number),
'number': 'FC2-'+number, 'number': 'FC2-'+number,
'cover': getCover(htmlcode2), 'cover': getCover(htmlcode,number,htmlcode2),
'imagecut': 0, 'imagecut': 0,
'tag': getTag(htmlcode2), 'tag': getTag(htmlcode),
'actor_photo':'', 'actor_photo':'',
'website': 'http://adult.contents.fc2.com/article_search.php?id=' + number, 'website': 'https://fc2club.com//html/FC2-' + number + '.html',
'source': 'fc2fans_club.py', 'source':'https://fc2club.com//html/FC2-' + number + '.html',
} }
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8') js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
return js return js
#print(main('1051725'))

51
javdb.py
View File

@ -4,7 +4,6 @@ import json
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from ADC_function import * from ADC_function import *
def getTitle(a): def getTitle(a):
try: try:
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
@ -12,98 +11,75 @@ def getTitle(a):
return re.sub('.*\] ', '', result.replace('/', ',').replace('\\xa0', '').replace(' : ', '')) return re.sub('.*\] ', '', result.replace('/', ',').replace('\\xa0', '').replace(' : ', ''))
except: except:
return re.sub('.*\] ', '', result.replace('/', ',').replace('\\xa0', '')) return re.sub('.*\] ', '', result.replace('/', ',').replace('\\xa0', ''))
def getActor(a): # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text() 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() 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(" ['']") 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(" ['']") 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(',,', return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',').replace(',', ', ')
'').lstrip( def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
',').replace(',', ', ') a = actor.split(',')
d={}
for i in a:
p={i:''}
d.update(p)
return d
def getStudio(a): def getStudio(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 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(" ['']") 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(" ['']") result2 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '') return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
def getRuntime(a): def getRuntime(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 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(" ['']") 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(" ['']") result2 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').rstrip('mi') return str(result1 + result2).strip('+').rstrip('mi')
def getLabel(a): def getLabel(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 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(" ['']") 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(" ['']") 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): def getNum(a):
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
result1 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/text()')).strip(" ['']") 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(" ['']") result2 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result2 + result1).strip('+') return str(result2 + result1).strip('+')
def getYear(getRelease): def getYear(getRelease):
try: try:
result = str(re.search('\d{4}', getRelease).group()) result = str(re.search('\d{4}', getRelease).group())
return result return result
except: except:
return getRelease return getRelease
def getRelease(a): def getRelease(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 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(" ['']") 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(" ['']") result2 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+') return str(result1 + result2).strip('+')
def getTag(a): def getTag(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 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(" ['']") 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(" ['']") 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(',,', return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',')
'').lstrip(
',')
def getCover_small(a): def getCover_small(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result = 'http:' + html.xpath( result = 'http:' + html.xpath(
'//div[@id=\'videos\']/div[@class=\'grid columns\']/div[@class=\'grid-item column\'][1]/a[' '//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] '@class=\'box\']/div[@class=\'item-image fix-scale-cover\']/img/@src')[0]
return result return result
def getCover(htmlcode): def getCover(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser()) html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('/html/body/section/div/div[2]/div[1]/a/img/@src')).strip(" ['']") result = str(html.xpath('/html/body/section/div/div[2]/div[1]/a/img/@src')).strip(" ['']")
if result == '': 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 return result
def getDirector(a): def getDirector(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 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(" ['']") 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(" ['']") 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): def getOutline(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser()) html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']") result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
return result return result
def main(number): def main(number):
number = number.upper() number = number.upper()
try: try:
@ -128,7 +104,7 @@ def main(number):
'tag': getTag(b), 'tag': getTag(b),
'label': getLabel(b), 'label': getLabel(b),
'year': getYear(getRelease(b)), # str(re.search('\d{4}',getRelease(a)).group()), 'year': getYear(getRelease(b)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': '', 'actor_photo': getActorPhoto(getActor(b)),
'website': 'https://javdb.com' + result1, 'website': 'https://javdb.com' + result1,
'source': 'javdb.py', 'source': 'javdb.py',
} }
@ -141,6 +117,7 @@ def main(number):
a = get_html('https://javdb.com/search?q=' + number + '&f=all').replace(u'\xa0', u' ') 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() html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = html.xpath('//*[@id="videos"]/div/div/a/@href')[0] 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' ') b = get_html('https://javdb.com' + result1).replace(u'\xa0', u' ')
dic = { dic = {
'actor': getActor(b), 'actor': getActor(b),
@ -160,7 +137,7 @@ def main(number):
'tag': getTag(b), 'tag': getTag(b),
'label': getLabel(b), 'label': getLabel(b),
'year': getYear(getRelease(b)), # str(re.search('\d{4}',getRelease(a)).group()), 'year': getYear(getRelease(b)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': '', 'actor_photo': getActorPhoto(getActor(b)),
'website': 'https://javdb.com' + result1, 'website': 'https://javdb.com' + result1,
'source': 'javdb.py', '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') js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js 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')) # print(get_html('https://javdb1.com/v/WwZ0Q'))

2
siro.py
View File

@ -101,3 +101,5 @@ def main(number2):
} }
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8') js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js return js
#print(main('SIRO-3607'))

4
update_check.json
View File

@ -1,5 +1,5 @@
{ {
"version": "1.9", "version": "2.1",
"version_show":"1.9", "version_show":"2.1",
"download": "https://github.com/yoshiko2/AV_Data_Capture/releases" "download": "https://github.com/yoshiko2/AV_Data_Capture/releases"
} }