update scrapinglib

- support specifiedUrl when scraping single movie
- support javlibrary and rating

scrapinglib/xcity.py

@@ -13,6 +13,9 @@ class Xcity(Parser):
 
     expr_number = '//*[@id="hinban"]/text()'
     expr_title = '//*[@id="program_detail_title"]/text()'
+    expr_actor = '//ul/li[@class="credit-links"]/a/text()'
+    expr_actor_link = '//ul/li[@class="credit-links"]/a'
+    expr_actorphoto = '//div[@class="frame"]/div/p/img/@src'
     expr_studio = '//*[@id="avodDetails"]/div/div[3]/div[2]/div/ul[1]/li[4]/a/span/text()'
     expr_studio2 = '//strong[contains(text(),"片商")]/../following-sibling::span/a/text()'
     expr_runtime = '//span[@class="koumoku" and text()="収録時間"]/../text()'
@@ -23,6 +26,7 @@ class Xcity(Parser):
     expr_director = '//*[@id="program_detail_director"]/text()'
     expr_series = "//span[contains(text(),'シリーズ')]/../a/span/text()"
     expr_series2 = "//span[contains(text(),'シリーズ')]/../span/text()"
+    expr_extrafanart = '//div[@id="sample_images"]/div/a/@href'
 
     def getStudio(self, htmltree):
         return super().getStudio(htmltree).strip('+').replace("', '", '').replace('"', '')
@@ -57,41 +61,29 @@ class Xcity(Parser):
             return getStoryline(self.number, uncensored=False)
         return ''
 
-    def getActors(self, htmltree):
-        htmla = self.browser.page.select('#avodDetails > div > div.frame > div.content > div > ul.profileCL > li.credit-links > a')
-        t = []
-        for i in htmla:
-            t.append(i.text.strip())
-        return t
-
     def getActorPhoto(self, htmltree):
-        htmla = self.browser.page.select('#avodDetails > div > div.frame > div.content > div > ul.profileCL > li.credit-links > a')
-        t = {i.text.strip(): i['href'] for i in htmla}
+        treea = self.getTreeAll(htmltree, self.expr_actor_link)
+        t = {i.text.strip(): i.attrib['href'] for i in treea}
         o = {}
         for k, v in t.items():
-            r = self.browser.open_relative(v)
-            if not r.ok:
-                continue
-            pic = self.browser.page.select_one('#avidolDetails > div > div.frame > div > p > img')
-            if 'noimage.gif' in pic['src']:
-                continue
-            o[k] = urljoin(self.browser.url, pic['src'])
+            actorpageUrl = "https://xcity.jp" + v
+            try:
+                adtree = self.getHtmlTree(actorpageUrl)
+                picUrl = self.getTreeElement(adtree, self.expr_actorphoto)
+                if 'noimage.gif' in picUrl:
+                    continue
+                o[k] = urljoin("https://xcity.jp", picUrl)
+            except:
+                pass
         return o
 
     def getExtrafanart(self, htmltree):
-        html_pather = re.compile(r'<div id="sample_images".*?>[\s\S]*?</div>')
-        html = html_pather.search(self.detail_page)
-        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 ''
+        arts = self.getTreeAll(htmltree, self.expr_extrafanart)
+        extrafanart = []
+        for i in arts:
+            i = "https:" + i
+            extrafanart.append(i)
+        return extrafanart
 
     def open_by_browser(self, number):
         xcity_number = number.replace('-','')
@@ -108,8 +100,12 @@ class Xcity(Parser):
 
     def search(self, number):
         self.number = number
-        self.detail_page, self.browser = self.open_by_browser(number)
-        self.detailurl = self.browser.url
-        lx = etree.fromstring(self.detail_page, etree.HTMLParser())
+        if self.specifiedUrl:
+            self.detailurl = self.specifiedUrl
+            lx = self.getHtmlTree(self.detailurl)
+        else:
+            self.detail_page, self.browser = self.open_by_browser(number)
+            self.detailurl = self.browser.url
+            lx = etree.fromstring(self.detail_page, etree.HTMLParser())
         result = self.dictformat(lx)
         return result