Merge pull request #991 from hejianjun/master

添加新的刮削网站Javmenu

core.py

@@ -272,7 +272,10 @@ def extrafanart_download_threadpool(url_list, save_dir, number, json_data=None):
 
 def image_ext(url):
     try:
-        return os.path.splitext(url)[-1]
+        ext = os.path.splitext(url)[-1]
+        if ext in {'.jpg','.jpge','.bmp','.png','.gif'}:
+            return ext
+        return ".jpg"
     except:
         return ".jpg"
 

number_parser.py

@@ -54,7 +54,7 @@ def get_number(debug: bool, file_path: str) -> str:
             filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath))  # 去除文件名中时间
             lower_check = filename.lower()
             if 'fc2' in lower_check:
-                filename = lower_check.replace('ppv', '').replace('--', '-').replace('_', '-').upper()
+                filename = lower_check.replace('--', '-').replace('_', '-').upper()
             filename = re.sub("[-_]cd\d{1,2}", "", filename, flags=re.IGNORECASE)
             if not re.search("-|_", filename): # 去掉-CD1之后再无-的情况，例如n1012-CD1.wmv
                 return str(re.search(r'\w+', filename[:filename.find('.')], re.A).group())

scrapinglib/api.py

@@ -21,6 +21,7 @@ from .avsox import Avsox
 from .javlibrary import Javlibrary
 from .javday import Javday
 from .pissplay import Pissplay
+from .javmenu import Javmenu
 
 from .tmdb import Tmdb
 from .imdb import Imdb
@@ -53,7 +54,7 @@ class Scraping:
     """
     adult_full_sources = ['javlibrary', 'javdb', 'javbus', 'airav', 'fanza', 'xcity', 'jav321',
                           'mgstage', 'fc2', 'avsox', 'dlsite', 'carib', 'madou', 
-                          'getchu', 'gcolle','javday','pissplay'
+                          'getchu', 'gcolle','javday','pissplay','javmenu'
                           ]
     adult_func_mapping = {
         'avsox': Avsox().scrape,
@@ -72,7 +73,8 @@ class Scraping:
         'getchu': Getchu().scrape,
         'javlibrary': Javlibrary().scrape,
         'javday': Javday().scrape,
-        'pissplay': Pissplay().scrape
+        'pissplay': Pissplay().scrape,
+        'javmenu': Javmenu().scrape
     }
 
     general_full_sources = ['tmdb', 'imdb']

scrapinglib/javmenu.py

@@ -0,0 +1,61 @@
+# -*- coding: utf-8 -*-
+
+import re
+from lxml import etree
+from urllib.parse import urljoin
+
+from .parser import Parser
+
+
+class Javmenu(Parser):
+    source = 'javmenu'
+
+    expr_title = '/html/head/meta[@property="og:title"]/@content'
+    expr_cover = '/html/head/meta[@property="og:image"]/@content'
+
+    expr_number = '//span[contains(text(),"番號") or contains(text(),"番号")]/../a/text()'
+    expr_number2 = '//span[contains(text(),"番號") or contains(text(),"番号")]/../span[2]/text()'
+    expr_runtime = '//span[contains(text(),"時長;") or contains(text(),"时长")]/../span[2]/text()'
+    expr_release = '//span[contains(text(),"日期")]/../span[2]/text()'
+    expr_studio = '//span[contains(text(),"製作")]/../span[2]/a/text()'
+
+    expr_actor = '//a[contains(@class,"actress")]/text()'
+    expr_tags = '//a[contains(@class,"genre")]/text()'
+
+    def extraInit(self):
+        self.imagecut = 4
+        self.uncensored = True
+
+    def search(self, number):
+        self.number = number
+        if self.specifiedUrl:
+            self.detailurl = self.specifiedUrl
+        else:
+            self.detailurl = 'https://javmenu.com/zh/' + self.number + '/'
+        self.htmlcode = self.getHtml(self.detailurl)
+        if self.htmlcode == 404:
+            return 404
+        htmltree = etree.HTML(self.htmlcode)
+        result = self.dictformat(htmltree)
+        return result
+
+    def getNum(self, htmltree):
+        # 番号被分割开，需要合并后才是完整番号
+        part1 = self.getTreeElement(htmltree, self.expr_number)
+        part2 = self.getTreeElement(htmltree, self.expr_number2)
+        dp_number =  part1 + part2
+        # NOTE 检测匹配与更新 self.number
+        if dp_number.upper() != self.number.upper():
+            raise Exception(f'[!] {self.number}: find [{dp_number}] in javmenu, not match')
+        self.number = dp_number
+        return self.number
+
+    def getTitle(self, htmltree):
+        browser_title = super().getTitle(htmltree)
+        # 删除番号
+        number = re.findall("\d+",self.number)[1]
+        title = browser_title.split(number,1)[-1]
+        title = title.replace(' | JAV目錄大全 | 每日更新',"")
+        title = title.replace(' | JAV目录大全 | 每日更新',"").strip()
+        return title.replace(self.number, '').strip()
+