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

Merge branch 'master' into patch-6

Browse Source
This commit is contained in:
Feng4
2020-12-29 17:35:49 +08:00
committed by GitHub
parent cbb2b2a0ca 3cc66021e9
commit 566cd7461f
15 changed files with 520 additions and 104 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
ADC_function.py
View File

@@ -1,6 +1,6 @@
import requests
from lxml import etree
import re
import config
SUPPORT_PROXY_TYPE = ("http", "socks5", "socks5h")
@@ -463,3 +463,14 @@ def translate(src:str,target_language:str="zh_cn"):
translate_list = [i["trans"] for i in result.json()["sentences"]]
return "".join(translate_list)
# ========================================================================是否为无码
def is_uncensored(number):
if re.match('^\d{4,}', number) or re.match('n\d{4}', number) or 'HEYZO' in number.upper():
return True
configs = config.Config().get_uncensored()
prefix_list = str(configs).split(',')
for pre in prefix_list:
if pre.upper() in number.upper():
return True
return False

BIN
Img/LEAK.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 13 KiB

BIN
Img/SUB.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 10 KiB

BIN
Img/UNCENSORED.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 11 KiB

100
WebCrawler/airav.py
View File

@@ -110,56 +110,65 @@ def getTag(htmlcode): # 获取标签
tag.append(i.get_text())
return tag
def getExtrafanart(htmlcode): # 获取剧照
html_pather = re.compile(r'<div class=\"mobileImgThumbnail\">[\s\S]*?</div></div></div></div>')
html = html_pather.search(htmlcode)
if html:
html = html.group()
extrafanart_pather = re.compile(r'<img.*?src=\"(.*?)\"')
extrafanart_imgs = extrafanart_pather.findall(html)
if extrafanart_imgs:
return extrafanart_imgs
return ''
def main(number):
try:
try:
try:
htmlcode = get_html('https://cn.airav.wiki/video/' + number)
javbus_htmlcode = get_html('https://www.javbus.com/ja/' + number)
htmlcode = get_html('https://cn.airav.wiki/video/' + number)
javbus_htmlcode = get_html('https://www.javbus.com/ja/' + number)
except:
print(number)
dic = {
# 标题可使用airav
'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
# 制作商选择使用javbus
'studio': getStudio(javbus_htmlcode),
# 年份也是用javbus
'year': str(re.search('\d{4}', getYear(javbus_htmlcode)).group()),
# 简介 使用 airav
'outline': getOutline(htmlcode),
# 使用javbus
'runtime': getRuntime(javbus_htmlcode),
# 导演 使用javbus
'director': getDirector(javbus_htmlcode),
# 作者 使用airav
'actor': getActor(htmlcode),
# 发售日使用javbus
'release': getRelease(javbus_htmlcode),
# 番号使用javbus
'number': getNum(javbus_htmlcode),
# 封面链接 使用javbus
'cover': getCover(javbus_htmlcode),
'imagecut': 1,
# 使用 airav
'tag': getTag(htmlcode),
# 使用javbus
'label': getSerise(javbus_htmlcode),
# 妈的，airav不提供作者图片
'actor_photo': getActorPhoto(javbus_htmlcode),
'website': 'https://www.airav.wiki/video/' + number,
'source': 'airav.py',
# 使用javbus
'series': getSerise(javbus_htmlcode),
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,separators=(',', ':'), ) # .encode('UTF-8')
return js
except:
return main_uncensored(number)
print(number)
dic = {
# 标题可使用airav
'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
# 制作商选择使用javbus
'studio': getStudio(javbus_htmlcode),
# 年份也是用javbus
'year': str(re.search('\d{4}', getYear(javbus_htmlcode)).group()),
# 简介 使用 airav
'outline': getOutline(htmlcode),
# 使用javbus
'runtime': getRuntime(javbus_htmlcode),
# 导演 使用javbus
'director': getDirector(javbus_htmlcode),
# 作者 使用airav
'actor': getActor(htmlcode),
# 发售日使用javbus
'release': getRelease(javbus_htmlcode),
# 番号使用javbus
'number': getNum(javbus_htmlcode),
# 封面链接 使用javbus
'cover': getCover(javbus_htmlcode),
# 剧照获取
'extrafanart': getExtrafanart(htmlcode),
'imagecut': 1,
# 使用 airav
'tag': getTag(htmlcode),
# 使用javbus
'label': getSerise(javbus_htmlcode),
# 妈的，airav不提供作者图片
'actor_photo': getActorPhoto(javbus_htmlcode),
'website': 'https://www.airav.wiki/video/' + number,
'source': 'airav.py',
# 使用javbus
'series': getSerise(javbus_htmlcode),
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,separators=(',', ':'), ) # .encode('UTF-8')
return js
except:
data = {
"title": "",
@@ -171,4 +180,5 @@ def main(number):
if __name__ == '__main__':
print(main('sdsi-019'))
print(main('ADN-188'))

21
WebCrawler/fanza.py
View File

@@ -209,6 +209,21 @@ def getSeries(text):
except:
return ""
def getExtrafanart(htmlcode): # 获取剧照
html_pather = re.compile(r'<div id=\"sample-image-block\"[\s\S]*?<br></div></div>')
html = html_pather.search(htmlcode)
if html:
html = html.group()
extrafanart_pather = re.compile(r'<img.*?src=\"(.*?)\"')
extrafanart_imgs = extrafanart_pather.findall(html)
if extrafanart_imgs:
s = []
for img_url in extrafanart_imgs:
img_urls = img_url.rsplit('-', 1)
img_url = img_urls[0] + 'jp-' + img_urls[1]
s.append(img_url)
return s
return ''
def main(number):
# fanza allow letter + number + underscore, normalize the input here
@@ -260,6 +275,7 @@ def main(number):
"cover": getCover(htmlcode, fanza_hinban),
"imagecut": 1,
"tag": getTag(htmlcode),
"extrafanart": getExtrafanart(htmlcode),
"label": getLabel(htmlcode),
"year": getYear(
getRelease(htmlcode)
@@ -309,5 +325,6 @@ def main_htmlcode(number):
if __name__ == "__main__":
print(main("DV-1562"))
print(main("96fad1217"))
# print(main("DV-1562"))
# print(main("96fad1217"))
print(main("pred00251"))

32
WebCrawler/fc2.py
View File

@@ -60,6 +60,29 @@ def getYear_fc2com(release):
except:
return ''
def getExtrafanart(htmlcode): # 获取剧照
html_pather = re.compile(r'<ul class=\"items_article_SampleImagesArea\"[\s\S]*?</ul>')
html = html_pather.search(htmlcode)
if html:
html = html.group()
extrafanart_pather = re.compile(r'<a href=\"(.*?)\"')
extrafanart_imgs = extrafanart_pather.findall(html)
if extrafanart_imgs:
return extrafanart_imgs
return ''
def getTrailer(htmlcode):
video_pather = re.compile(r'\'[a-zA-Z0-9]{32}\'')
video = video_pather.findall(htmlcode)
if video:
video_url = video[0].replace('\'', '')
video_url = 'https://adult.contents.fc2.com/api/v2/videos/1603395/sample?key=' + video_url
url_json = eval(ADC_function.get_html(video_url))['path'].replace('\\', '')
else:
video_url = ''
return url_json
def main(number):
try:
number = number.replace('FC2-', '').replace('fc2-', '')
@@ -70,7 +93,7 @@ def main(number):
dic = {
'title': getTitle_fc2com(htmlcode2),
'studio': getStudio_fc2com(htmlcode2),
'year': str(re.search('\d{4}', getRelease_fc2com(htmlcode2)).group()),
'year': getYear_fc2com(getRelease_fc2com(htmlcode2)),
'outline': '', # getOutline_fc2com(htmlcode2),
'runtime': '',
'director': getStudio_fc2com(htmlcode2),
@@ -79,6 +102,8 @@ def main(number):
'number': 'FC2-' + number,
'label': '',
'cover': getCover_fc2com(htmlcode2),
'extrafanart': getExtrafanart(htmlcode2),
"trailer": getTrailer(htmlcode2),
'imagecut': 0,
'tag': getTag_fc2com(number),
'actor_photo': '',
@@ -87,10 +112,11 @@ def main(number):
'series': '',
}
except Exception as e:
# print(e)
print(e)
dic = {"title": ""}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
if __name__ == '__main__':
print(main('1228742'))
print(main('FC2-1603395'))

27
WebCrawler/jav321.py
View File

@@ -4,15 +4,18 @@ import json
from bs4 import BeautifulSoup
from lxml import html
from ADC_function import post_html
import re
def main(number: str) -> json:
result = post_html(url="https://www.jav321.com/search", query={"sn": number})
soup = BeautifulSoup(result.text, "html.parser")
lx = html.fromstring(str(soup))
if "/video/" in result.url:
data = parse_info(soup)
dic = {
"title": get_title(lx),
"year": get_year(data),
@@ -20,6 +23,8 @@ def main(number: str) -> json:
"director": "",
"cover": get_cover(lx),
"imagecut": 1,
"trailer": get_trailer(result.text),
"extrafanart": get_extrafanart(result.text),
"actor_photo": "",
"website": result.url,
"source": "jav321.py",
@@ -30,7 +35,6 @@ def main(number: str) -> json:
return json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'))
def get_title(lx: html.HtmlElement) -> str:
return lx.xpath("/html/body/div[2]/div[1]/div[1]/div[1]/h3/text()")[0].strip()
@@ -79,6 +83,24 @@ def get_anchor_info(h: str) -> str:
def get_text_info(h: str) -> str:
return h.split(": ")[1]
def get_trailer(html) -> str:
videourl_pather = re.compile(r'<source src=\"(.*?)\"')
videourl = videourl_pather.findall(html)
if videourl:
return videourl[0]
else:
return ''
def get_extrafanart(htmlcode): # 获取剧照
html_pather = re.compile(r'<div class=\"col\-md\-3\"><div class=\"col\-xs\-12 col\-md\-12\">[\s\S]*?</script><script async src=\"\/\/adserver\.juicyads\.com/js/jads\.js\">')
html = html_pather.search(htmlcode)
if html:
html = html.group()
extrafanart_pather = re.compile(r'<img.*?src=\"(.*?)\"')
extrafanart_imgs = extrafanart_pather.findall(html)
if extrafanart_imgs:
return extrafanart_imgs
return ''
def get_cover(lx: html.HtmlElement) -> str:
return lx.xpath("/html/body/div[2]/div[2]/div[1]/p/a/img/@src")[0]
@@ -112,6 +134,7 @@ def get_tag(data: hash) -> str:
return ""
def get_studio(data: hash) -> str:
if "片商" in data:
return get_anchor_info(data["片商"])
@@ -155,4 +178,4 @@ def get_series(data: hash) -> str:
if __name__ == "__main__":
print(main("soe-259"))
print(main("jul-404"))

13
WebCrawler/javbus.py
View File

@@ -107,6 +107,17 @@ def getTag(htmlcode): # 获取标签
tag.append(translateTag_to_sc(i.get_text()))
return tag
def getExtrafanart(htmlcode): # 获取剧照
html_pather = re.compile(r'<div id=\"sample-waterfall\">[\s\S]*?</div></a>\s*?</div>')
html = html_pather.search(htmlcode)
if html:
html = html.group()
extrafanart_pather = re.compile(r'<a class=\"sample-box\" href=\"(.*?)\"')
extrafanart_imgs = extrafanart_pather.findall(html)
if extrafanart_imgs:
return extrafanart_imgs
return ''
def main_uncensored(number):
htmlcode = get_html('https://www.javbus.com/ja/' + number)
if getTitle(htmlcode) == '':
@@ -127,6 +138,7 @@ def main_uncensored(number):
'number': getNum(htmlcode),
'cover': getCover(htmlcode),
'tag': getTag(htmlcode),
'extrafanart': getExtrafanart(htmlcode),
'label': getSerise(htmlcode),
'imagecut': 0,
'actor_photo': '',
@@ -162,6 +174,7 @@ def main(number):
'cover': getCover(htmlcode),
'imagecut': 1,
'tag': getTag(htmlcode),
'extrafanart': getExtrafanart(htmlcode),
'label': getSerise(htmlcode),
'actor_photo': getActorPhoto(htmlcode),
'website': 'https://www.javbus.com/' + number,

105
WebCrawler/javdb.py
View File

@@ -18,18 +18,38 @@ def getActor(a): # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]
result1 = str(html.xpath('//strong[contains(text(),"演員")]/../span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"演員")]/../span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').replace('N/A', '').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 getaphoto(url):
html_page = get_html(url)
img_prether = re.compile(r'<span class\=\"avatar\" style\=\"background\-image\: url\((.*?)\)')
img_url = img_prether.findall(html_page)
if img_prether:
return img_url[0]
else:
return ''
def getActorPhoto(html): #//*[@id="star_qdt"]/li/a/img
actorall_prether = re.compile(r'<strong>演員\:</strong>\s*?.*?<span class=\"value\">(.*)\s*?</div>')
actorall = actorall_prether.findall(html)
if actorall:
actoralls = actorall[0]
actor_prether = re.compile(r'<a href\=\"(.*?)\">(.*?)</a>')
actor = actor_prether.findall(actoralls)
actor_photo = {}
for i in actor:
actor_photo[i[1]] = getaphoto('https://javdb.com'+i[0])
return actor_photo
else:
return {}
def getStudio(a):
# html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
# result1 = str(html.xpath('//strong[contains(text(),"片商")]/../span/text()')).strip(" ['']")
# result2 = str(html.xpath('//strong[contains(text(),"片商")]/../span/a/text()')).strip(" ['']")
# return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
# html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
# result1 = str(html.xpath('//strong[contains(text(),"片商")]/../span/text()')).strip(" ['']")
# result2 = str(html.xpath('//strong[contains(text(),"片商")]/../span/a/text()')).strip(" ['']")
# return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
patherr = re.compile(r'<strong>片商\:</strong>[\s\S]*?<a href=\".*?>(.*?)</a></span>')
pianshang = patherr.findall(a)
if pianshang:
@@ -37,6 +57,7 @@ def getStudio(a):
else:
result = ""
return result
def getRuntime(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"時長")]/../span/text()')).strip(" ['']")
@@ -53,11 +74,11 @@ def getNum(a):
result2 = str(html.xpath('//strong[contains(text(),"番號")]/../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
# try:
# result = str(re.search('\d{4}', getRelease).group())
# return result
# except:
# return getRelease
patherr = re.compile(r'<strong>日期\:</strong>\s*?.*?<span class="value">(.*?)\-.*?</span>')
dates = patherr.findall(getRelease)
if dates:
@@ -65,11 +86,12 @@ def getYear(getRelease):
else:
result = ''
return result
def getRelease(a):
# html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
# result1 = str(html.xpath('//strong[contains(text(),"時間")]/../span/text()')).strip(" ['']")
# result2 = str(html.xpath('//strong[contains(text(),"時間")]/../span/a/text()')).strip(" ['']")
# return str(result1 + result2).strip('+')
# html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
# result1 = str(html.xpath('//strong[contains(text(),"時間")]/../span/text()')).strip(" ['']")
# result2 = str(html.xpath('//strong[contains(text(),"時間")]/../span/a/text()')).strip(" ['']")
# return str(result1 + result2).strip('+')
patherr = re.compile(r'<strong>日期\:</strong>\s*?.*?<span class="value">(.*?)</span>')
dates = patherr.findall(a)
if dates:
@@ -121,6 +143,30 @@ def getCover_small(a, index=0):
result = 'https:' + result
return result
def getTrailer(htmlcode): # 获取预告片
video_pather = re.compile(r'<video id\=\".*?>\s*?<source src=\"(.*?)\"')
video = video_pather.findall(htmlcode)
if video:
if not 'https:' in video[0]:
video_url = 'https:' + video[0]
else:
video_url = video[0]
else:
video_url = ''
return video_url
def getExtrafanart(htmlcode): # 获取剧照
html_pather = re.compile(r'<div class=\"tile\-images preview\-images\">[\s\S]*?</a>\s+?</div>\s+?</div>')
html = html_pather.search(htmlcode)
if html:
html = html.group()
extrafanart_pather = re.compile(r'<a class="tile-item" href=\"(.*?)\"')
extrafanart_imgs = extrafanart_pather.findall(html)
if extrafanart_imgs:
return extrafanart_imgs
return ''
def getCover(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser())
try:
@@ -145,6 +191,10 @@ def getSeries(a):
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
def main(number):
try:
# if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number).group():
# pass
# else:
# number = number.upper()
number = number.upper()
try:
query_result = get_html('https://javdb.com/search?q=' + number + '&f=all')
@@ -161,7 +211,6 @@ def main(number):
else:
ids =html.xpath('//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()')
correct_url = urls[ids.index(number)]
detail_page = get_html('https://javdb.com' + correct_url)
# no cut image by default
@@ -171,7 +220,6 @@ def main(number):
cover_small = getCover_small(query_result)
else:
cover_small = getCover_small(query_result, index=ids.index(number))
if 'placeholder' in cover_small:
# replace wit normal cover and cut it
imagecut = 1
@@ -194,17 +242,20 @@ def main(number):
'number': number,
'cover': getCover(detail_page),
'cover_small': cover_small,
'trailer': getTrailer(detail_page),
'extrafanart': getExtrafanart(detail_page),
'imagecut': imagecut,
'tag': getTag(detail_page),
'label': getLabel(detail_page),
'year': getYear(getRelease(detail_page)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': getActorPhoto(getActor(detail_page)),
'year': getYear(detail_page), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': getActorPhoto(detail_page),
'website': 'https://javdb.com' + correct_url,
'source': 'javdb.py',
'series': getSeries(detail_page),
}
except Exception as e:
# print(e)
print(e)
dic = {"title": ""}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
@@ -212,4 +263,6 @@ def main(number):
# 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('ipx-292'))
# print(main('blacked.20.05.30'))
# print(main('AGAV-042'))
print(main('BANK-022'))

13
WebCrawler/mgstage.py
View File

@@ -95,6 +95,18 @@ def getSeries(a):
result2 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
def getExtrafanart(htmlcode): # 获取剧照
html_pather = re.compile(r'<dd>\s*?<ul>[\s\S]*?</ul>\s*?</dd>')
html = html_pather.search(htmlcode)
if html:
html = html.group()
extrafanart_pather = re.compile(r'<a class=\"sample_image\" href=\"(.*?)\"')
extrafanart_imgs = extrafanart_pather.findall(html)
if extrafanart_imgs:
return extrafanart_imgs
return ''
def main(number2):
number=number2.upper()
htmlcode=str(get_html('https://www.mgstage.com/product/product_detail/'+str(number)+'/',cookies={'adc':'1'}))
@@ -115,6 +127,7 @@ def main(number2):
'imagecut': 0,
'tag': getTag(a),
'label':getLabel(a),
'extrafanart': getExtrafanart(htmlcode),
'year': getYear(getRelease(a)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': '',
'website':'https://www.mgstage.com/product/product_detail/'+str(number)+'/',

15
WebCrawler/xcity.py
View File

@@ -154,6 +154,20 @@ def getSeries(htmlcode):
except:
return ''
def getExtrafanart(htmlcode): # 获取剧照
html_pather = re.compile(r'<div id="sample_images".*?>[\s\S]*?</div>')
html = html_pather.search(htmlcode)
if html:
html = html.group()
extrafanart_pather = re.compile(r'<a.*?href=\"(.*?)\"')
extrafanart_imgs = extrafanart_pather.findall(html)
if extrafanart_imgs:
s = []
for urli in extrafanart_imgs:
urli = 'https:' + urli.replace('/scene/small', '')
s.append(urli)
return s
return ''
def main(number):
try:
@@ -174,6 +188,7 @@ def main(number):
'number': getNum(detail_page),
'cover': getCover(detail_page),
'cover_small': '',
'extrafanart': getExtrafanart(detail_page),
'imagecut': 1,
'tag': getTag(detail_page),
'label': getLabel(detail_page),

26
config.ini
View File

@@ -36,3 +36,29 @@ switch=0
[transalte]
switch=0
values=title,outline
; 预告片
[trailer]
switch=1
; 用来确定是否是无码
[uncensored]
uncensored_prefix=S2M,BT,LAF,SMD
[media]
; 影片后缀
media_type=.mp4,.avi,.rmvb,.wmv,.mov,.mkv,.flv,.ts,.webm,.MP4,.AVI,.RMVB,.WMV,.MOV,.MKV,.FLV,.TS,.WEBM,iso,ISO
; 字幕后缀
sub_type=.smi,.srt,.idx,.sub,.sup,.psb,.ssa,.ass,.txt,.usf,.xss,.ssf,.rt,.lrc,.sbv,.vtt,.ttml
; 水印
[watermark]
switch=1
water=2
; 左上 0, 右上 1, 右下 2， 左下 3
; 剧照
[extrafanart]
switch=1
extrafanart_folder=extrafanart

58
config.py
View File

@@ -45,6 +45,35 @@ class Config:
return self.conf.getboolean("common", "transalte_to_sc")
def is_transalte(self) -> bool:
return self.conf.getboolean("transalte", "switch")
def is_trailer(self) -> bool:
return self.conf.getboolean("trailer", "switch")
def is_watermark(self) -> bool:
return self.conf.getboolean("watermark", "switch")
def is_extrafanart(self) -> bool:
return self.conf.getboolean("extrafanart", "switch")
def watermark_type(self) -> int:
return int(self.conf.get("watermark", "water"))
def get_uncensored(self):
try:
sec = "uncensored"
uncensored_prefix = self.conf.get(sec, "uncensored_prefix")
# uncensored_poster = self.conf.get(sec, "uncensored_poster")
return uncensored_prefix
except ValueError:
self._exit("uncensored")
def get_extrafanart(self):
try:
extrafanart_download = self.conf.get("extrafanart", "extrafanart_folder")
return extrafanart_download
except ValueError:
self._exit("extrafanart_folder")
def transalte_values(self) -> bool:
return self.conf.get("transalte", "values")
def proxy(self) -> [str, int, int, str]:
@@ -58,7 +87,13 @@ class Config:
return switch, proxy, timeout, retry, proxytype
except ValueError:
self._exit("common")
def media_rule(self) -> str:
return self.conf.get('media', 'media_type').replace(',', '|')
def sub_rule(self):
return self.conf.get('media', 'sub_type').split(',')
def naming_rule(self) -> str:
return self.conf.get("Name_Rule", "naming_rule")
@@ -146,6 +181,29 @@ class Config:
conf.add_section(sec8)
conf.set(sec8, "switch", "0")
conf.set(sec8, "values", "title,outline")
sec9 = "trailer"
conf.add_section(sec9)
conf.set(sec9, "switch", "0")
sec10 = "uncensored"
conf.add_section(sec10)
conf.set(sec10, "uncensored_prefix", "S2M,BT,LAF,SMD")
sec11 = "media"
conf.add_section(sec11)
conf.set(sec11, "media_type", ".mp4,.avi,.rmvb,.wmv,.mov,.mkv,.flv,.ts,.webm,.MP4,.AVI,.RMVB,.WMV,.MOV,.MKV,.FLV,.TS,.WEBM,iso,ISO")
conf.set(sec11, "sub_type", ".smi,.srt,.idx,.sub,.sup,.psb,.ssa,.ass,.txt,.usf,.xss,.ssf,.rt,.lrc,.sbv,.vtt,.ttml")
sec12 = "watermark"
conf.add_section(sec12)
conf.set(sec12, "switch", 1)
conf.set(sec12, "water", 2)
sec13 = "extrafanart"
conf.add_section(sec13)
conf.set(sec13, "switch", 1)
conf.set(sec13, "extrafanart_folder", "extrafanart")
return conf

201
core.py
View File

@@ -34,7 +34,7 @@ def moveFailedFolder(filepath, failed_folder):
root_path = str(pathlib.Path(filepath).parent)
file_name = pathlib.Path(filepath).name
destination_path = root_path + '/' + failed_folder + '/'
if config.Config.soft_link():
if config.Config().soft_link():
print('[-]Create symlink to Failed output folder')
os.symlink(filepath, destination_path + '/' + file_name)
else:
@@ -127,7 +127,17 @@ def get_data_from_json(file_number, filepath, conf: config.Config): # 从JSON
cover_small = ''
else:
cover_small = json_data.get('cover_small')
if json_data.get('trailer') == None:
trailer = ''
else:
trailer = json_data.get('trailer')
if json_data.get('extrafanart') == None:
extrafanart = ''
else:
extrafanart = json_data.get('extrafanart')
imagecut = json_data.get('imagecut')
tag = str(json_data.get('tag')).strip("[ ]").replace("'", '').replace(" ", '').split(',') # 字符串转列表 @
actor = str(actor_list).strip("[ ]").replace("'", '').replace(" ", '')
@@ -217,6 +227,23 @@ def get_data_from_json(file_number, filepath, conf: config.Config): # 从JSON
translate_values = conf.transalte_values().split(",")
for translate_value in translate_values:
json_data[translate_value] = translate(json_data[translate_value])
if conf.is_trailer():
if trailer:
json_data['trailer'] = trailer
else:
json_data['trailer'] = ''
else:
json_data['trailer'] = ''
if conf.is_extrafanart():
if extrafanart:
json_data['extrafanart'] = extrafanart
else:
json_data['extrafanart'] = ''
else:
json_data['extrafanart'] = ''
naming_rule=""
for i in conf.naming_rule().split("+"):
if i not in json_data:
@@ -238,10 +265,11 @@ def get_info(json_data): # 返回json里的数据
release = json_data.get('release')
number = json_data.get('number')
cover = json_data.get('cover')
trailer = json_data.get('trailer')
website = json_data.get('website')
series = json_data.get('series')
label = json_data.get('label', "")
return title, studio, year, outline, runtime, director, actor_photo, release, number, cover, website, series, label
return title, studio, year, outline, runtime, director, actor_photo, release, number, cover, trailer, website, series, label
def small_cover_check(path, number, cover_small, c_word, conf: config.Config, filepath, failed_folder):
@@ -250,7 +278,7 @@ def small_cover_check(path, number, cover_small, c_word, conf: config.Config, fi
def create_folder(success_folder, location_rule, json_data, conf: config.Config): # 创建文件夹
title, studio, year, outline, runtime, director, actor_photo, release, number, cover, website, series, label = get_info(json_data)
title, studio, year, outline, runtime, director, actor_photo, release, number, cover, trailer, website, series, label = get_info(json_data)
if len(location_rule) > 240: # 新建成功输出文件夹
path = success_folder + '/' + location_rule.replace("'actor'", "'manypeople'", 3).replace("actor","'manypeople'",3) # path为影片+元数据所在目录
else:
@@ -326,6 +354,44 @@ def download_file_with_filename(url, filename, path, conf: config.Config, filepa
moveFailedFolder(filepath, failed_folder)
return
def trailer_download(trailer, c_word, number, path, filepath, conf: config.Config, failed_folder):
if download_file_with_filename(trailer, number + c_word + '-trailer.mp4', path, conf, filepath, failed_folder) == 'failed':
return
switch, _proxy, _timeout, retry, _proxytype = conf.proxy()
for i in range(retry):
if os.path.getsize(path+'/' + number + c_word + '-trailer.mp4') == 0:
print('[!]Video Download Failed! Trying again. [{}/3]', i + 1)
download_file_with_filename(trailer, number + c_word + '-trailer.mp4', path, conf, filepath, failed_folder)
continue
else:
break
if os.path.getsize(path + '/' + number + c_word + '-trailer.mp4') == 0:
return
print('[+]Video Downloaded!', path + '/' + number + c_word + '-trailer.mp4')
# 剧照下载成功，否则移动到failed
def extrafanart_download(data, path, conf: config.Config, filepath, failed_folder):
j = 1
path = path + '/' + conf.get_extrafanart()
for url in data:
if download_file_with_filename(url, '/extrafanart-' + str(j)+'.jpg', path, conf, filepath, failed_folder) == 'failed':
moveFailedFolder(filepath, failed_folder)
return
switch, _proxy, _timeout, retry, _proxytype = conf.proxy()
for i in range(retry):
if os.path.getsize(path + '/extrafanart-' + str(j) + '.jpg') == 0:
print('[!]Image Download Failed! Trying again. [{}/3]', i + 1)
download_file_with_filename(url, '/extrafanart-' + str(j)+'.jpg', path, conf, filepath,
failed_folder)
continue
else:
break
if os.path.getsize(path + '/extrafanart-' + str(j) + '.jpg') == 0:
return
print('[+]Image Downloaded!', path + '/extrafanart-' + str(j) + '.jpg')
j += 1
# 封面是否下载成功，否则移动到failed
def image_download(cover, number, c_word, path, conf: config.Config, filepath, failed_folder):
@@ -348,7 +414,7 @@ def image_download(cover, number, c_word, path, conf: config.Config, filepath, f
def print_files(path, c_word, naming_rule, part, cn_sub, json_data, filepath, failed_folder, tag, actor_list, liuchu):
title, studio, year, outline, runtime, director, actor_photo, release, number, cover, website, series, label = get_info(json_data)
title, studio, year, outline, runtime, director, actor_photo, release, number, cover, trailer, website, series, label = get_info(json_data)
try:
if not os.path.exists(path):
@@ -397,6 +463,7 @@ def print_files(path, c_word, naming_rule, part, cn_sub, json_data, filepath, fa
print(" <num>" + number + "</num>", file=code)
print(" <premiered>" + release + "</premiered>", file=code)
print(" <cover>" + cover + "</cover>", file=code)
print(" <trailer>" + trailer + "</trailer>", file=code)
print(" <website>" + website + "</website>", file=code)
print("</movie>", file=code)
print("[+]Wrote! " + path + "/" + number + part + c_word + ".nfo")
@@ -428,9 +495,70 @@ def cutImage(imagecut, path, number, c_word):
shutil.copyfile(path + '/' + number + c_word + '-fanart.jpg',path + '/' + number + c_word + '-poster.jpg')
print('[+]Image Copyed! ' + path + '/' + number + c_word + '-poster.jpg')
# 此函数从gui版copy过来用用
# 参数说明
# poster_path
# thumb_path
# cn_sub 中文字幕 参数值为 1 0
# leak 流出 参数值为 1 0
# uncensored 无码 参数值为 1 0
# ========================================================================加水印
def add_mark(poster_path, thumb_path, cn_sub, leak, uncensored, conf:config.Config):
mark_type = ''
if cn_sub:
mark_type += ',字幕'
if leak:
mark_type += ',流出'
if uncensored:
mark_type += ',无码'
add_mark_thread(thumb_path, cn_sub, leak, uncensored, conf)
print('[+]Thumb Add Mark: ' + mark_type.strip(','))
add_mark_thread(poster_path, cn_sub, leak, uncensored, conf)
print('[+]Poster Add Mark: ' + mark_type.strip(','))
def add_mark_thread(pic_path, cn_sub, leak, uncensored, conf):
size = 14
img_pic = Image.open(pic_path)
# 获取自定义位置，取余配合pos达到顺时针添加的效果
# 左上 0, 右上 1, 右下 2， 左下 3
count = conf.watermark_type()
if cn_sub == 1 or cn_sub == '1':
add_to_pic(pic_path, img_pic, size, count, 1) # 添加
count = (count + 1) % 4
if leak == 1 or leak == '1':
add_to_pic(pic_path, img_pic, size, count, 2)
count = (count + 1) % 4
if uncensored == 1 or uncensored == '1':
add_to_pic(pic_path, img_pic, size, count, 3)
img_pic.close()
def add_to_pic(pic_path, img_pic, size, count, mode):
mark_pic_path = ''
if mode == 1:
mark_pic_path = 'Img/SUB.png'
elif mode == 2:
mark_pic_path = 'Img/LEAK.png'
elif mode == 3:
mark_pic_path = 'Img/UNCENSORED.png'
img_subt = Image.open(mark_pic_path)
scroll_high = int(img_pic.height / size)
scroll_wide = int(scroll_high * img_subt.width / img_subt.height)
img_subt = img_subt.resize((scroll_wide, scroll_high), Image.ANTIALIAS)
r, g, b, a = img_subt.split() # 获取颜色通道，保持png的透明性
# 封面四个角的位置
pos = [
{'x': 0, 'y': 0},
{'x': img_pic.width - scroll_wide, 'y': 0},
{'x': img_pic.width - scroll_wide, 'y': img_pic.height - scroll_high},
{'x': 0, 'y': img_pic.height - scroll_high},
]
img_pic.paste(img_subt, (pos[count]['x'], pos[count]['y']), mask=a)
img_pic.save(pic_path, quality=95)
# ========================结束=================================
def paste_file_to_folder(filepath, path, number, c_word, conf: config.Config): # 文件路径，番号，后缀，要移动至的位置
houzhui = str(re.search('[.](iso|ISO|AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|WEBM|avi|rmvb|wmv|mov|mp4|mkv|flv|ts|webm)$', filepath).group())
media_res = conf.media_rule()
houzhui = str(re.search(media_res + '$', filepath).group())
file_parent_origin_path = str(pathlib.Path(filepath).parent)
try:
# 如果soft_link=1 使用软链接
@@ -438,15 +566,14 @@ def paste_file_to_folder(filepath, path, number, c_word, conf: config.Config):
os.symlink(filepath, path + '/' + number + c_word + houzhui)
else:
os.rename(filepath, path + '/' + number + c_word + houzhui)
if os.path.exists(file_parent_origin_path + '/' + number + c_word + '.srt'): # 字幕移动
os.rename(file_parent_origin_path + '/' + number + c_word + '.srt', path + '/' + number + c_word + '.srt')
print('[+]Sub moved!')
elif os.path.exists(file_parent_origin_path + '/' + number + c_word + '.ssa'):
os.rename(file_parent_origin_path + '/' + number + c_word + '.ssa', path + '/' + number + c_word + '.ssa')
print('[+]Sub moved!')
elif os.path.exists(file_parent_origin_path + '/' + number + c_word + '.sub'):
os.rename(file_parent_origin_path + '/' + number + c_word + '.sub', path + '/' + number + c_word + '.sub')
print('[+]Sub moved!')
sub_res = conf.sub_rule()
for subname in sub_res:
if os.path.exists(os.getcwd() + '/' + number + c_word + subname): # 字幕移动
os.rename(os.getcwd() + '/' + number + c_word + subname, path + '/' + number + c_word + subname)
print('[+]Sub moved!')
return True
except FileExistsError:
print('[-]File Exists! Please check your movie!')
print('[-]move to the root folder of the program.')
@@ -459,23 +586,22 @@ def paste_file_to_folder(filepath, path, number, c_word, conf: config.Config):
def paste_file_to_folder_mode2(filepath, path, multi_part, number, part, c_word, conf): # 文件路径，番号，后缀，要移动至的位置
if multi_part == 1:
number += part # 这时number会被附加上CD1后缀
houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|WEBM|avi|rmvb|wmv|mov|mp4|mkv|flv|ts|webm|iso|ISO)$', filepath).group())
media_res = conf.media_rule()
houzhui = str(re.search(media_res + '$', filepath).group())
file_parent_origin_path = str(pathlib.Path(filepath).parent)
try:
if conf.soft_link():
os.symlink(filepath, path + '/' + number + part + c_word + houzhui)
else:
os.rename(filepath, path + '/' + number + part + c_word + houzhui)
if os.path.exists(file_parent_origin_path + '/' + number + '.srt'): # 字幕移动
os.rename(file_parent_origin_path + '/' + number + part + c_word + '.srt', path + '/' + number + part + c_word + '.srt')
print('[+]Sub moved!')
elif os.path.exists(file_parent_origin_path + '/' + number + part + c_word + '.ass'):
os.rename(file_parent_origin_path + '/' + number + part + c_word + '.ass', path + '/' + number + part + c_word + '.ass')
print('[+]Sub moved!')
elif os.path.exists(file_parent_origin_path + '/' + number + part + c_word + '.sub'):
os.rename(file_parent_origin_path + '/' + number + part + c_word + '.sub', path + '/' + number + part + c_word + '.sub')
print('[+]Sub moved!')
print('[!]Success')
sub_res = conf.sub_rule()
for subname in sub_res:
if os.path.exists(os.getcwd() + '/' + number + c_word + subname): # 字幕移动
os.rename(os.getcwd() + '/' + number + c_word + subname, path + '/' + number + c_word + subname)
print('[+]Sub moved!')
print('[!]Success')
return True
except FileExistsError:
print('[-]File Exists! Please check your movie!')
print('[-]move to the root folder of the program.')
@@ -547,8 +673,19 @@ def core_main(file_path, number_th, conf: config.Config):
if '-c.' in filepath or '-C.' in filepath or '中文' in filepath or '字幕' in filepath:
cn_sub = '1'
c_word = '-C' # 中文字幕影片后缀
# 判断是否无码
if is_uncensored(number):
uncensored = 1
else:
uncensored = 0
if '流出' in filepath:
liuchu = '流出'
leak = 1
else:
leak = 0
# 调试模式检测
if conf.debug():
@@ -574,6 +711,14 @@ def core_main(file_path, number_th, conf: config.Config):
# creatFolder会返回番号路径
image_download( json_data.get('cover'), number, c_word, path, conf, filepath, conf.failed_folder())
# 下载预告片
if json_data.get('trailer'):
trailer_download(json_data.get('trailer'), c_word, number, path, filepath, conf, conf.failed_folder())
# 下载剧照 data, path, conf: config.Config, filepath, failed_folder
if json_data.get('extrafanart'):
extrafanart_download(json_data.get('extrafanart'), path, conf, filepath, conf.failed_folder())
# 裁剪图
cutImage(imagecut, path, number, c_word)
@@ -582,6 +727,12 @@ def core_main(file_path, number_th, conf: config.Config):
# 移动文件
paste_file_to_folder(filepath, path, number, c_word, conf)
poster_path = path + '/' + number + c_word + '-poster.jpg'
thumb_path = path + '/' + number + c_word + '-thumb.jpg'
if conf.is_watermark():
add_mark(poster_path, thumb_path, cn_sub, leak, uncensored, conf)
elif conf.main_mode() == 2:
# 创建文件夹
path = create_folder(conf.success_folder(), json_data.get('location_rule'), json_data, conf)