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

0.6 更新:Javbus抓取的元数据支持标签功能，优化无码视频抓取

Browse Source
This commit is contained in:
wenead99 2019-06-02 23:10:01 +08:00 committed by GitHub
parent cfccd00367
commit 532c5bfbe3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 124 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

74
core.py
View File

@ -16,11 +16,12 @@ year=''
outline='' outline=''
runtime='' runtime=''
director='' director=''
actor='' actor=[]
release='' release=''
number='' number=''
cover='' cover=''
imagecut='' imagecut=''
tag=[]
#=====================资源下载部分=========================== #=====================资源下载部分===========================
def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder! def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder!
@ -58,12 +59,21 @@ def PrintFiles(path):
print(" <poster>" + number + ".png</poster>", file=code) print(" <poster>" + number + ".png</poster>", file=code)
print(" <thumb>" + number + ".png</thumb>", file=code) print(" <thumb>" + number + ".png</thumb>", file=code)
print(" <fanart>"+number + '.jpg'+"</fanart>", file=code) print(" <fanart>"+number + '.jpg'+"</fanart>", file=code)
print(" <actor>", file=code) try:
print(" <name>" + actor + "</name>", file=code) for u in actor:
print(" </actor>", file=code) print(" <actor>", file=code)
print(" <name>" + u + "</name>", file=code)
print(" </actor>", file=code)
except:
aaaa=''
print(" <maker>" + studio + "</maker>", file=code) print(" <maker>" + studio + "</maker>", file=code)
print(" <label>", file=code) print(" <label>", file=code)
print(" </label>", file=code) print(" </label>", file=code)
try:
for i in tag:
print(" <tag>" + i + "</tag>", file=code)
except:
aaaa=''
print(" <num>" + number + "</num>", file=code) print(" <num>" + number + "</num>", file=code)
print(" <release>" + release + "</release>", file=code) print(" <release>" + release + "</release>", file=code)
print(" <cover>"+cover+"</cover>", file=code) print(" <cover>"+cover+"</cover>", file=code)
@ -96,34 +106,47 @@ def getNumberFromFilename(filepath):
global number global number
global cover global cover
global imagecut global imagecut
global tag
filename = str(os.path.basename(filepath)) #电影文件名 filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", os.path.basename(filepath)))
str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filename))
print("[!]Making Data for ["+filename+"]") print("[!]Making Data for ["+filename+"]")
a = str(re.search('\w+-\w+', filename).group()) file_number = str(re.search('\w+-\w+', filename).group())
#print(a) #print(a)
# =======================网站规则添加==============================
try: try:
try:
if re.search('^\d{5,}', a).group() in filename:
json_data = json.loads(javbus.main_uncensored(a.replace("-", "_")))
except:
#================================================网站规则添加开始================================================
try: #添加 需要 正则表达式的规则
if re.search('^\d{5,}', file_number).group() in filename:
json_data = json.loads(javbus.main_uncensored(file_number))
except: #添加 无需 正则表达式的规则
if 'fc2' in filename: if 'fc2' in filename:
json_data = json.loads(fc2fans_club.main(a)) json_data = json.loads(fc2fans_club.main(file_number))
elif 'FC2' in filename: elif 'FC2' in filename:
json_data = json.loads(fc2fans_club.main(a)) json_data = json.loads(fc2fans_club.main(file_number))
elif 'siro' in filename: elif 'siro' in filename:
json_data = json.loads(siro.main(a)) json_data = json.loads(siro.main(file_number))
elif 'SIRO' in filename: elif 'SIRO' in filename:
json_data = json.loads(siro.main(a)) json_data = json.loads(siro.main(file_number))
elif '259luxu' in filename: elif '259luxu' in filename:
json_data = json.loads(siro.main(a)) json_data = json.loads(siro.main(file_number))
elif '259LUXU' in filename: elif '259LUXU' in filename:
json_data = json.loads(siro.main(a)) json_data = json.loads(siro.main(file_number))
else: else:
json_data = json.loads(javbus.main(a)) json_data = json.loads(javbus.main(file_number))
# ====================网站规则添加结束==============================
#================================================网站规则添加结束================================================
title = json_data['title'] title = json_data['title']
studio = json_data['studio'] studio = json_data['studio']
@ -131,11 +154,12 @@ def getNumberFromFilename(filepath):
outline = json_data['outline'] outline = json_data['outline']
runtime = json_data['runtime'] runtime = json_data['runtime']
director = json_data['director'] director = json_data['director']
actor = json_data['actor'] actor = str(json_data['actor']).strip("[ ]").replace("'",'').replace(" ",'').split(',')
release = json_data['release'] release = json_data['release']
number = json_data['number'] number = json_data['number']
cover = json_data['cover'] cover = json_data['cover']
imagecut = json_data['imagecut'] imagecut = json_data['imagecut']
tag = str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',')
except: except:
print('[-]File '+filename+'`s number can not be caught') print('[-]File '+filename+'`s number can not be caught')
print('[-]Move ' + filename + ' to failed folder') print('[-]Move ' + filename + ' to failed folder')
@ -151,19 +175,21 @@ def getNumberFromFilename(filepath):
path = '' #设置path为全局变量，后面移动文件要用 path = '' #设置path为全局变量，后面移动文件要用
def creatFolder(): def creatFolder():
actor2 = str(actor).strip("[ ]").replace("'",'').replace(" ",'')
global path global path
if not os.path.exists('failed/'): #新建failed文件夹 if not os.path.exists('failed/'): #新建failed文件夹
os.makedirs('failed/') os.makedirs('failed/')
if not os.path.exists('failed/'): if not os.path.exists('failed/'):
print("[-]failed!Dirs can not be make (Please run as Administrator)") print("[-]failed!Dirs can not be make (Please run as Administrator)")
os._exit(0) os._exit(0)
if len(actor) > 240: #新建成功输出文件夹 if len(actor2) > 240: #新建成功输出文件夹
path = 'JAV_output' + '/' + '超多人' + '/' + number #path为影片+元数据所在目录 path = 'JAV_output' + '/' + '超多人' + '/' + number #path为影片+元数据所在目录
else: else:
path = 'JAV_output' + '/' + str(actor) + '/' + str(number) path = 'JAV_output' + '/' + str(actor2) + '/' + str(number)
if not os.path.exists(path): if not os.path.exists(path):
os.makedirs(path) os.makedirs(path)
path = str(os.getcwd())+'/'+path path = str(os.getcwd())+'/'+path
def imageDownload(filepath): #封面是否下载成功，否则移动到failed def imageDownload(filepath): #封面是否下载成功，否则移动到failed
if DownloadFileWithFilename(cover,str(number) + '.jpg', path) == 'failed': if DownloadFileWithFilename(cover,str(number) + '.jpg', path) == 'failed':
shutil.move(filepath, 'failed/') shutil.move(filepath, 'failed/')

6
fc2fans_club.py
View File

@ -31,6 +31,11 @@ def getOutline(htmlcode,number): #获取番号
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).replace("\\n",'',10000).strip(" ['']").replace("'",'',10000) result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).replace("\\n",'',10000).strip(" ['']").replace("'",'',10000)
return result return result
# def getTag(htmlcode,number): #获取番号
# 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(a, etree.HTMLParser())
# result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).replace("\\n",'',10000).strip(" ['']").replace("'",'',10000)
# return result
def main(number): def main(number):
str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-") str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")
@ -47,6 +52,7 @@ def main(number):
'number': number, 'number': number,
'cover': getCover(htmlcode,number), 'cover': getCover(htmlcode,number),
'imagecut': 0, 'imagecut': 0,
'tag':" ",
} }
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

81
javbus.py
View File

@ -29,8 +29,7 @@ def getStudio(htmlcode): #获取厂商
def getYear(htmlcode): #获取年份 def getYear(htmlcode): #获取年份
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[2]/text()')).strip(" ['']") result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
result2 = str(re.search('\d{4}', result).group(0)) return result
return result2
def getCover(htmlcode): #获取封面链接 def getCover(htmlcode): #获取封面链接
doc = pq(htmlcode) doc = pq(htmlcode)
image = doc('a.bigImage') image = doc('a.bigImage')
@ -49,8 +48,8 @@ def getActor(htmlcode): #获取女优
soup=BeautifulSoup(htmlcode,'lxml') soup=BeautifulSoup(htmlcode,'lxml')
a=soup.find_all(attrs={'class':'star-name'}) a=soup.find_all(attrs={'class':'star-name'})
for i in a: for i in a:
b.append(i.text) b.append(i.get_text())
return ",".join(b) return b
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(" ['']")
@ -64,6 +63,18 @@ def getOutline(htmlcode): #获取演员
result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text()) result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text())
return result return result
def getTag(htmlcode): # 获取演员
tag = []
soup = BeautifulSoup(htmlcode, 'lxml')
a = soup.find_all(attrs={'class': 'genre'})
for i in a:
if 'onmouseout' in str(i):
continue
tag.append(i.get_text())
return tag
def main(number): def main(number):
htmlcode=get_html('https://www.javbus.com/'+number) htmlcode=get_html('https://www.javbus.com/'+number)
dww_htmlcode=get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", '')) dww_htmlcode=get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
@ -79,28 +90,58 @@ def main(number):
'number': getNum(htmlcode), 'number': getNum(htmlcode),
'cover': getCover(htmlcode), 'cover': getCover(htmlcode),
'imagecut': 1, 'imagecut': 1,
'tag':getTag(htmlcode)
} }
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
def main_uncensored(number): def main_uncensored(number):
htmlcode=get_html('https://www.javbus.com/'+number) htmlcode = get_html('https://www.javbus.com/' + number)
dww_htmlcode=get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", '')) dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
#print('un')
#print('https://www.javbus.com/' + number)
dic = { dic = {
'title': getTitle(htmlcode), 'title': getTitle(htmlcode),
'studio': getStudio(htmlcode), 'studio': getStudio(htmlcode),
'year': getYear(htmlcode), 'year': getYear(htmlcode),
'outline': getOutline(dww_htmlcode), 'outline': getOutline(htmlcode),
'runtime': getRuntime(htmlcode), 'runtime': getRuntime(htmlcode),
'director': getDirector(htmlcode), 'director': getDirector(htmlcode),
'actor': getActor(htmlcode), 'actor': getActor(htmlcode),
'release': getRelease(htmlcode), 'release': getRelease(htmlcode),
'number': getNum(htmlcode), 'number': getNum(htmlcode),
'cover': getCover(htmlcode), 'cover': getCover(htmlcode),
'tag': getTag(htmlcode),
'imagecut': 0, 'imagecut': 0,
} }
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
if getYear(htmlcode) == '':
#print('un2')
number2 = number.replace('-', '_')
htmlcode = get_html('https://www.javbus.com/' + number2)
#print('https://www.javbus.com/' + number2)
dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number2.replace("_", ''))
dic = {
'title': getTitle(htmlcode),
'studio': getStudio(htmlcode),
'year': getYear(htmlcode),
'outline': getOutline(htmlcode),
'runtime': getRuntime(htmlcode),
'director': getDirector(htmlcode),
'actor': getActor(htmlcode),
'release': getRelease(htmlcode),
'number': getNum(htmlcode),
'cover': getCover(htmlcode),
'tag': getTag(htmlcode),
'imagecut': 0,
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
#print(js)
return js
else:
bbb=''
# def return1(): # def return1():
# json_data=json.loads(main('ipx-292')) # json_data=json.loads(main('ipx-292'))
@ -115,15 +156,17 @@ def main_uncensored(number):
# release = str(json_data['release']) # release = str(json_data['release'])
# number = str(json_data['number']) # number = str(json_data['number'])
# cover = str(json_data['cover']) # cover = str(json_data['cover'])
# tag = str(json_data['tag'])
# #
# # print(title) # print(title)
# # print(studio) # print(studio)
# # print(year) # print(year)
# # print(outline) # print(outline)
# # print(runtime) # print(runtime)
# # print(director) # print(director)
# # print(actor) # print(actor)
# # print(release) # print(release)
# # print(number) # print(number)
# # print(cover) # print(cover)
# print(tag)
# return1() # return1()

7
siro.py
View File

@ -42,6 +42,10 @@ def getRelease(a):
html = etree.fromstring(a, etree.HTMLParser()) html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n ']") result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n ']")
return result return result
def getTag(a):
html = etree.fromstring(a, etree.HTMLParser())
result=str(html.xpath('//table[2]/tr[9]/td/text()')).strip(" ['\\n ']")
return result
def getCover(htmlcode): def getCover(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser()) html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('//*[@id="center_column"]/div[2]/div[1]/div/div/h2/img/@src')).strip(" ['']") result = str(html.xpath('//*[@id="center_column"]/div[2]/div[1]/div/div/h2/img/@src')).strip(" ['']")
@ -58,7 +62,7 @@ def getOutline(htmlcode):
def main(number): def main(number):
htmlcode=get_html('https://www.mgstage.com/product/product_detail/'+str(number)) htmlcode=get_html('https://www.mgstage.com/product/product_detail/'+str(number))
soup = BeautifulSoup(htmlcode, 'lxml') soup = BeautifulSoup(htmlcode, 'lxml')
a = str(soup.find(attrs={'class': 'detail_data'})) a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n ','')
dic = { dic = {
'title': getTitle(htmlcode).replace("\\n",'').replace(' ',''), 'title': getTitle(htmlcode).replace("\\n",'').replace(' ',''),
'studio': getStudio(a), 'studio': getStudio(a),
@ -71,6 +75,7 @@ def main(number):
'number': number, 'number': number,
'cover': getCover(htmlcode), 'cover': getCover(htmlcode),
'imagecut': 0, 'imagecut': 0,
'tag':' ',
} }
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