From e91b7a85bf0ab6227c18ebbc77e30872338d442c Mon Sep 17 00:00:00 2001 From: wenead99 <42309414+wenead99@users.noreply.github.com> Date: Mon, 17 Jun 2019 16:14:17 +0800 Subject: [PATCH] 0.10 Beta10 Update --- ADC_function.py | 41 +++----- core.py | 263 ++++++++++++++++++++++++------------------------ fc2fans_club.py | 8 +- javbus.py | 43 ++++++-- proxy.ini | 16 +++ 5 files changed, 201 insertions(+), 170 deletions(-) create mode 100644 proxy.ini diff --git a/ADC_function.py b/ADC_function.py index 62006fe..e356b5b 100644 --- a/ADC_function.py +++ b/ADC_function.py @@ -12,33 +12,24 @@ else: def get_html(url):#网页请求核心 if not str(config['proxy']['proxy']) == '': + proxies = { + "http" : "http://" + str(config['proxy']['proxy']), + "https": "https://" + str(config['proxy']['proxy']) + } + headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'} + getweb = requests.get(str(url), headers=headers, proxies=proxies) + getweb.encoding = 'utf-8' + # print(getweb.text) try: - proxies = {"http": "http://" + str(config['proxy']['proxy']), - "https": "https://" + str(config['proxy']['proxy'])} - headers = { - 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'} - getweb = requests.get(str(url), timeout=10, headers=headers, proxies=proxies) - getweb.encoding = 'utf-8' - # print(getweb.text) - try: - return getweb.text - except: - print('[-]Connected failed!:Proxy error') + return getweb.text except: - aaaa='' - #print('[-]Connect Failed.') - - + print('[-]Connected failed!:Proxy error') else: + headers = { + 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'} + getweb = requests.get(str(url), headers=headers) + getweb.encoding = 'utf-8' try: - headers = { - 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'} - getweb = requests.get(str(url), timeout=10, headers=headers) - getweb.encoding = 'utf-8' - try: - return getweb.text - except: - print("[-]Connect Failed.") + return getweb.text except: - aaaa = '' - #print('[-]Connect Failed.') \ No newline at end of file + print("[-]Connect Failed.") \ No newline at end of file diff --git a/core.py b/core.py index adb394b..4013eeb 100644 --- a/core.py +++ b/core.py @@ -18,109 +18,15 @@ year='' outline='' runtime='' director='' -actor=[] +actor_list=[] +actor='' release='' number='' cover='' imagecut='' tag=[] - -#=====================资源下载部分=========================== -def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder! - config = ConfigParser() - config.read('proxy.ini', encoding='UTF-8') - proxy = str(config['proxy']['proxy']) - - if not str(config['proxy']['proxy']) == '': - try: - if not os.path.exists(path): - os.makedirs(path) - headers = { - 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'} - r = requests.get(url,timeout=10, headers=headers,proxies={"http": "http://" + str(proxy), "https": "https://" + str(proxy)}) - with open(str(path) + "/" + str(filename), "wb") as code: - code.write(r.content) - # print(bytes(r),file=code) - except IOError as e: - print("[-]Movie not found in All website!") - print("[-]" + str(filename), e) - # print("[*]=====================================") - return "failed" - except Exception as e1: - print(e1) - print("[-]Download Failed2!") - time.sleep(3) - os._exit(0) - else: - try: - if not os.path.exists(path): - os.makedirs(path) - headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'} - r = requests.get(url,timeout=10, headers=headers) - with open(str(path) + "/" + str(filename), "wb") as code: - code.write(r.content) - # print(bytes(r),file=code) - except IOError as e: - print("[-]Movie not found in All website!") - print("[-]" + str(filename), e) - # print("[*]=====================================") - return "failed" - except Exception as e1: - print(e1) - print("[-]Download Failed2!") - time.sleep(3) - os._exit(0) -def PrintFiles(path): - try: - if not os.path.exists(path): - os.makedirs(path) - with open(path + "/" + number + ".nfo", "wt", encoding='UTF-8') as code: - print("", file=code) - print(" " + title + "", file=code) - print(" ", file=code) - print(" ", file=code) - print(" " + studio + "+", file=code) - print(" " + year + "", file=code) - print(" "+outline+"", file=code) - print(" "+outline+"", file=code) - print(" "+str(runtime).replace(" ","")+"", file=code) - print(" " + director + "", file=code) - print(" " + number + ".png", file=code) - print(" " + number + ".png", file=code) - print(" "+number + '.jpg'+"", file=code) - try: - for u in actor: - print(" ", file=code) - print(" " + u + "", file=code) - print(" ", file=code) - except: - aaaa='' - print(" " + studio + "", file=code) - print(" ", file=code) - try: - for i in tag: - print(" " + i + "", file=code) - except: - aaaaa='' - try: - for i in tag: - print(" " + i + "", file=code) - except: - aaaaaaaa='' - print(" " + number + "", file=code) - print(" " + release + "", file=code) - print(" "+cover+"", file=code) - print(" " + "https://www.javbus.com/"+number + "", file=code) - print("", file=code) - print("[+]Writeed! "+path + "/" + number + ".nfo") - except IOError as e: - print("[-]Write Failed!") - print(e) - except Exception as e1: - print(e1) - print("[-]Write Failed!") - +naming_rule =''#eval(config['Name_Rule']['naming_rule']) +location_rule=''#eval(config['Name_Rule']['location_rule']) #=====================本地文件处理=========================== def argparse_get_file(): import argparse @@ -135,7 +41,6 @@ def CreatFailedFolder(): except: print("[-]failed!can not be make folder 'failed'\n[-](Please run as Administrator)") os._exit(0) - def getNumberFromFilename(filepath): global title global studio @@ -143,6 +48,7 @@ def getNumberFromFilename(filepath): global outline global runtime global director + global actor_list global actor global release global number @@ -150,6 +56,9 @@ def getNumberFromFilename(filepath): global imagecut global tag + global naming_rule + global location_rule + #================================================获取文件番号================================================ try: #试图提取番号 # ====番号获取主程序==== @@ -170,7 +79,7 @@ def getNumberFromFilename(filepath): if not re.search('\w-', file_number).group() == 'None': file_number = re.search('\w+-\w+', filename).group() #上面是插入减号-到番号中 - print("[!]Making Data for [" + filename + "],the number is [" + file_number + "]") + print("[!]Making Data for [" + filename + "],the number is [" + file_number + "]") # ====番号获取主程序=结束=== except Exception as e: #番号提取异常 print('[-]'+str(os.path.basename(filepath))+' Cannot catch the number :') @@ -235,20 +144,22 @@ def getNumberFromFilename(filepath): - title = json_data['title'] - studio = json_data['studio'] - year = json_data['year'] - outline = json_data['outline'] - runtime = json_data['runtime'] - director = json_data['director'] - actor = str(json_data['actor']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表 - release = json_data['release'] - number = json_data['number'] - cover = json_data['cover'] - imagecut = json_data['imagecut'] - tag = str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表 - + title = json_data['title'] + studio = json_data['studio'] + year = json_data['year'] + outline = json_data['outline'] + runtime = json_data['runtime'] + director = json_data['director'] + actor_list= str(json_data['actor']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表 + release = json_data['release'] + number = json_data['number'] + cover = json_data['cover'] + imagecut = json_data['imagecut'] + tag = str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表 + actor = str(actor_list).strip("[ ]").replace("'",'').replace(" ",'') + naming_rule = eval(config['Name_Rule']['naming_rule']) + location_rule =eval(config['Name_Rule']['location_rule']) except IOError as e: print('[-]'+str(e)) print('[-]Move ' + filename + ' to failed folder') @@ -260,47 +171,137 @@ def getNumberFromFilename(filepath): print('[-]Move ' + filename + ' to failed folder') shutil.move(filepath, str(os.getcwd())+'/'+'failed/') os._exit(0) - path = '' #设置path为全局变量，后面移动文件要用 - def creatFolder(): - actor2 = str(actor).strip("[ ]").replace("'",'').replace(" ",'') global path - 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 + if len(actor) > 240: #新建成功输出文件夹 + path = location_rule.replace("'actor'","'超多人'",3).replace("actor","'超多人'",3) #path为影片+元数据所在目录 + #print(path) else: - path = 'JAV_output' + '/' + str(actor2) + '/' + str(number) + path = location_rule + #print(path) if not os.path.exists(path): os.makedirs(path) - path = str(os.getcwd())+'/'+path - +#=====================资源下载部分=========================== +def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder! + config = ConfigParser() + config.read('proxy.ini', encoding='UTF-8') + proxy = str(config['proxy']['proxy']) + if not str(config['proxy']['proxy']) == '': + try: + if not os.path.exists(path): + os.makedirs(path) + headers = { + 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'} + r = requests.get(url, headers=headers,proxies={"http": "http://" + str(proxy), "https": "https://" + str(proxy)}) + with open(str(path) + "/" + filename, "wb") as code: + code.write(r.content) + # print(bytes(r),file=code) + except IOError as e: + print("[-]Movie not found in All website!") + print("[-]" + filename, e) + # print("[*]=====================================") + return "failed" + except Exception as e1: + print(e1) + print("[-]Download Failed2!") + time.sleep(3) + os._exit(0) + else: + try: + if not os.path.exists(path): + os.makedirs(path) + headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'} + r = requests.get(url, headers=headers) + with open(str(path) + "/" + filename, "wb") as code: + code.write(r.content) + # print(bytes(r),file=code) + except IOError as e: + print("[-]Movie not found in All website!") + print("[-]" + filename, e) + # print("[*]=====================================") + return "failed" + except Exception as e1: + print(e1) + print("[-]Download Failed2!") + time.sleep(3) + os._exit(0) +def PrintFiles(path): + try: + if not os.path.exists(path): + os.makedirs(path) + with open(path + "/" + naming_rule + ".nfo", "wt", encoding='UTF-8') as code: + print("", file=code) + print(" " + title + "", file=code) + print(" ", file=code) + print(" ", file=code) + print(" " + studio + "+", file=code) + print(" " + year + "", file=code) + print(" "+outline+"", file=code) + print(" "+outline+"", file=code) + print(" "+str(runtime).replace(" ","")+"", file=code) + print(" " + director + "", file=code) + print(" " + naming_rule + ".png", file=code) + print(" " + naming_rule + ".png", file=code) + print(" "+naming_rule + '.jpg'+"", file=code) + try: + for u in actor_list: + print(" ", file=code) + print(" " + u + "", file=code) + print(" ", file=code) + except: + aaaa='' + print(" " + studio + "", file=code) + print(" ", file=code) + try: + for i in tag: + print(" " + i + "", file=code) + except: + aaaaa='' + try: + for i in tag: + print(" " + i + "", file=code) + except: + aaaaaaaa='' + print(" " + number + "", file=code) + print(" " + release + "", file=code) + print(" "+cover+"", file=code) + print(" " + "https://www.javbus.com/"+number + "", file=code) + print("", file=code) + print("[+]Writeed! "+path + "/" + naming_rule + ".nfo") + except IOError as e: + print("[-]Write Failed!") + print(e) + except Exception as e1: + print(e1) + print("[-]Write 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,naming_rule+ '.jpg', path) == 'failed': shutil.move(filepath, 'failed/') os._exit(0) - DownloadFileWithFilename(cover, number + '.jpg', path) - print('[+]Image Downloaded!', path +'/'+number+'.jpg') + DownloadFileWithFilename(cover, naming_rule + '.jpg', path) + print('[+]Image Downloaded!', path +'/'+naming_rule+'.jpg') def cutImage(): if imagecut == 1: try: - img = Image.open(path + '/' + number + '.jpg') + img = Image.open(path + '/' + naming_rule + '.jpg') imgSize = img.size w = img.width h = img.height img2 = img.crop((w / 1.9, 0, w, h)) - img2.save(path + '/' + number + '.png') + img2.save(path + '/' + naming_rule + '.png') except: print('[-]Cover cut failed!') else: - img = Image.open(path + '/' + number + '.jpg') + img = Image.open(path + '/' + naming_rule + '.jpg') w = img.width h = img.height - img.save(path + '/' + number + '.png') - + img.save(path + '/' + naming_rule + '.png') def pasteFileToFolder(filepath, path): #文件路径，番号，后缀，要移动至的位置 houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|avi|rmvb|wmv|mov|mp4|mkv|flv)$', filepath).group()) - os.rename(filepath, number + houzhui) - shutil.move(number + houzhui, path) + os.rename(filepath, naming_rule + houzhui) + shutil.move(naming_rule + houzhui, path) if __name__ == '__main__': filepath=argparse_get_file() #影片的路径 diff --git a/fc2fans_club.py b/fc2fans_club.py index d854ce8..27482e7 100644 --- a/fc2fans_club.py +++ b/fc2fans_club.py @@ -43,16 +43,18 @@ def main(number): dic = { 'title': getTitle(htmlcode), 'studio': getStudio(htmlcode), - 'year': getRelease(number), + 'year': str(re.search('\d{4}',getRelease(number)).group()), 'outline': getOutline(htmlcode,number), 'runtime': '', 'director': getStudio(htmlcode), 'actor': '', 'release': getRelease(number), - 'number': number, + 'number': 'FC2-'+number, 'cover': getCover(htmlcode,number), 'imagecut': 0, 'tag':" ", } 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('1104989')) \ No newline at end of file diff --git a/javbus.py b/javbus.py index 2b8744b..da62764 100644 --- a/javbus.py +++ b/javbus.py @@ -79,20 +79,41 @@ def main(number): htmlcode=get_html('https://www.javbus.com/'+number) dww_htmlcode=get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", '')) dic = { - 'title': getTitle(htmlcode), - 'studio': getStudio(htmlcode), - 'year': getYear(htmlcode), - 'outline': getOutline(dww_htmlcode), - 'runtime': getRuntime(htmlcode), + 'title': getTitle(htmlcode), + 'studio': getStudio(htmlcode), + 'year': str(re.search('\d{4}',getYear(htmlcode)).group()), + 'outline': getOutline(dww_htmlcode), + 'runtime': getRuntime(htmlcode), 'director': getDirector(htmlcode), - 'actor': getActor(htmlcode), - 'release': getRelease(htmlcode), - 'number': getNum(htmlcode), - 'cover': getCover(htmlcode), + 'actor': getActor(htmlcode), + 'release': getRelease(htmlcode), + 'number': getNum(htmlcode), + 'cover': getCover(htmlcode), 'imagecut': 1, - 'tag':getTag(htmlcode) + 'tag': getTag(htmlcode) } js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8') + + if 'HEYZO' in number or 'heyzo' in number or 'Heyzo' in number: + htmlcode = get_html('https://www.javbus.com/' + number) + dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", '')) + dic = { + 'title': getTitle(htmlcode), + 'studio': getStudio(htmlcode), + 'year': getYear(htmlcode), + 'outline': getOutline(dww_htmlcode), + 'runtime': getRuntime(htmlcode), + 'director': getDirector(htmlcode), + 'actor': getActor(htmlcode), + 'release': getRelease(htmlcode), + 'number': getNum(htmlcode), + 'cover': getCover(htmlcode), + 'imagecut': 1, + 'tag': getTag(htmlcode) + } + js2 = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8') + return js2 + return js def main_uncensored(number): @@ -120,7 +141,7 @@ def main_uncensored(number): 'title': getTitle(htmlcode), 'studio': getStudio(htmlcode), 'year': getYear(htmlcode), - 'outline': getOutline(htmlcode), + 'outline': '', 'runtime': getRuntime(htmlcode), 'director': getDirector(htmlcode), 'actor': getActor(htmlcode), diff --git a/proxy.ini b/proxy.ini new file mode 100644 index 0000000..a2e75d3 --- /dev/null +++ b/proxy.ini @@ -0,0 +1,16 @@ +[proxy] +proxy=127.0.0.1:1080 + +[Name_Rule] +location_rule='JAV_output/'+actor+'/'+actor+'-'+year+'- '+title+'['+number+']' +naming_rule=actor+'-'+year+'- '+title+'['+number+']' +#============================================================ +# +# title=标题,number=番号，stdio=片商,year=年份,director=导演，actor=女优，outline=简介 +# runtime=时长，release=上市日期，cover=封面URL，tag=类型 +# 例子: +# rule=str('JAV_output/'+actor+'/'+actor+' '+' ['+year+']'+title+' ['+number+']') +# 例子结束 +# 自定义字符(字符串)要加冒号'(内容)'，字符串连接要用加号+ +# +#============================================================ \ No newline at end of file