Merge pull request #913 from hejianjun/master

弃用91mv,换用新网站javday

scrapinglib/api.py

@@ -11,7 +11,6 @@ from .gcolle import Gcolle
 from .getchu import Getchu
 from .jav321 import Jav321
 from .javdb import Javdb
-from .mv91 import Mv91
 from .fc2 import Fc2
 from .madou import Madou
 from .mgstage import Mgstage
@@ -19,6 +18,7 @@ from .javbus import Javbus
 from .xcity import Xcity
 from .avsox import Avsox
 from .javlibrary import Javlibrary
+from .javday import Javday
 
 from .tmdb import Tmdb
 from .imdb import Imdb
@@ -50,8 +50,8 @@ class Scraping:
     """
     """
     adult_full_sources = ['javlibrary', 'javdb', 'javbus', 'airav', 'fanza', 'xcity', 'jav321',
-                          'mgstage', 'fc2', 'avsox', 'dlsite', 'carib', 'madou', 'mv91',
-                          'getchu', 'gcolle'
+                          'mgstage', 'fc2', 'avsox', 'dlsite', 'carib', 'madou', 
+                          'getchu', 'gcolle','javday'
                           ]
     adult_func_mapping = {
         'avsox': Avsox().scrape,
@@ -65,11 +65,11 @@ class Scraping:
         'fanza': Fanza().scrape,
         'airav': Airav().scrape,
         'carib': Carib().scrape,
-        'mv91': Mv91().scrape,
         'gcolle': Gcolle().scrape,
         'javdb': Javdb().scrape,
         'getchu': Getchu().scrape,
         'javlibrary': Javlibrary().scrape,
+        'javday': Javday().scrape
     }
 
     general_full_sources = ['tmdb', 'imdb']

scrapinglib/javday.py

@@ -0,0 +1,43 @@
+# -*- coding: utf-8 -*-
+
+import re
+from lxml import etree
+from urllib.parse import urlparse, unquote
+from .parser import Parser
+
+
+class Javday(Parser):
+    source = 'javday'
+
+    expr_url = '/html/head/meta[@property="og:url"]/@content'
+    expr_cover = '/html/head/meta[@property="og:image"]/@content'
+    expr_tags = '/html/head/meta[@name="keywords"]/@content'
+    expr_title = "/html/head/title/text()"
+    expr_actor = "//span[@class='vod_actor']/a/text()"
+    expr_studio = '//span[@class="producer"]/a/text()'
+    expr_number = '//span[@class="jpnum"]/text()'
+
+    def extraInit(self):
+        self.imagecut = 4
+        self.uncensored = True
+
+    def search(self, number):
+        self.number = number.strip().upper()
+        if self.specifiedUrl:
+            self.detailurl = self.specifiedUrl
+        else:
+            self.detailurl = "https://javday.tv/videos/" + self.number.replace("-","") + "/"
+        self.htmlcode = self.getHtml(self.detailurl)
+        if self.htmlcode == 404:
+            return 404
+        htmltree = etree.fromstring(self.htmlcode, etree.HTMLParser())
+        self.detailurl = self.getTreeElement(htmltree, self.expr_url)
+
+        result = self.dictformat(htmltree)
+        return result
+
+    def getTitle(self, htmltree):
+        title = super().getTitle(htmltree)
+        # 删除番号和网站名
+        result = title.replace(self.number,"").replace("- JAVDAY.TV","").strip()
+        return result

scrapinglib/mv91.py

@@ -1,94 +0,0 @@
-# -*- coding: utf-8 -*-
-
-
-import re
-from lxml import etree
-from .parser import Parser
-
-
-class Mv91(Parser):
-    source = 'mv91'
-
-    expr_number = '//div[@class="player-title"]/text()'
-    expr_title = '//div[@class="player-title"]/text()'
-    expr_release = '//p[@class="date"]/text()'
-    expr_outline = '//div[@class="play-text"]/text()'
-    expr_tags = '//div[@class="player-tag"]/text()'
-    expr_actor = '//p[@class="player-name"]/text()'
-
-    def extraInit(self):
-        self.imagecut = 0
-        self.uncensored = True
-
-    def getHtmlTree(self, url, type=None):
-        self.htmlcode = self.getHtml(url, type)
-        if self.htmlcode == 404:
-            return 404
-        ret = etree.fromstring(self.htmlcode, etree.HTMLParser())
-        return ret
-
-    def queryNumberUrl(self, number):
-        keyword = number.replace('91CM-','').replace('91MS-','')
-        search_html = self.getHtml('https://www.91mv.org/index/search?keywords=' + keyword)
-        html = etree.fromstring(search_html, etree.HTMLParser())
-        endurl = html.xpath('//a[@class="video-list"]/@href')[0]
-        return 'https://www.91mv.org' + endurl
-
-    def getNum(self, htmltree):
-        try:
-            num = super().getNum(htmltree)
-            finds = re.findall('(.*)(91.*-\d*)',num)
-            if finds:
-                result = str(finds[0][1])
-            else:
-                result = ' '.join(num.replace('/',' ').split())
-                result = result.split()[1]
-                if self.number.upper() != result.upper():
-                    raise Exception(f'[!] {self.number}: find {result} in mv91, not match')
-            return result.strip()
-        except:
-            return ''
-
-    def getTitle(self, htmltree):
-        try:
-            title = super().getTitle(htmltree)
-            finds = re.findall('(.*)(91.*-\d*)',title)
-            if finds:
-                result = str(finds[0][0])
-            else:
-                result = ' '.join(title.replace('/',' ').split())
-                result = result.split()[0]
-            return result.replace('「预告」','').strip('/ ')
-        except:
-            return ''
-
-    def getStudio(self, htmltree):
-        return '91制片厂'
-
-    def getActors(self, htmltree):
-        b=[]
-        for player in self.getTreeAll(htmltree, self.expr_actor):
-            player = player.replace('主演：','')
-            if '/' in player:
-                player = player.split('/')[0]
-                player = re.sub(r'[0-9]+', '', player)
-            b.append(player)
-        return b
-
-    def getRelease(self, htmltree):
-        try:
-            result = super().getRelease(htmltree)
-            date = result.replace('日期：','')
-            if isinstance(date, str) and len(date):
-                return date
-        except:
-            pass
-        return ''
-
-    def getCover(self, htmltree):
-        try:
-            url = str(re.findall('var pic_url = "(.*?)"', self.htmlcode)[0])
-            return url.strip()
-        except:
-            return ''
-