From fc4cc4c122785da7690f11465a5cd2bc301b0e2f Mon Sep 17 00:00:00 2001
From: Feng4 <wuxiang198@gmail.com>
Date: Sun, 20 Dec 2020 00:42:58 +0800
Subject: [PATCH] =?UTF-8?q?=E5=A2=9E=E5=8A=A0=E6=AC=A7=E7=BE=8E=E7=9A=84?=
 =?UTF-8?q?=E5=88=AE=E5=89=8A=E5=88=A4=E6=96=AD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 WebCrawler/javdb.py | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/WebCrawler/javdb.py b/WebCrawler/javdb.py
index eac8d7a..fa38bae 100644
--- a/WebCrawler/javdb.py
+++ b/WebCrawler/javdb.py
@@ -103,10 +103,17 @@ def getCover_small(a, index=0):
             result = 'https:' + result
         return result
     except: # 2020.7.17 Repair Cover Url crawl
-        result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@data-src")[index]
-        if not 'https' in result:
-            result = 'https:' + result
-        return result
+        try:
+            result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@data-src")[index]
+            if not 'https' in result:
+                result = 'https:' + result
+            return result
+        except:
+            result = html.xpath("//div[@class='item-image']/img/@data-src")[index]
+            if not 'https' in result:
+                result = 'https:' + result
+            return result
+
 def getCover(htmlcode):
     html = etree.fromstring(htmlcode, etree.HTMLParser())
     try:
@@ -141,14 +148,23 @@ def main(number):
         # and the first elememt maybe not the one we are looking for
         # iterate all candidates and find the match one
         urls = html.xpath('//*[@id="videos"]/div/div/a/@href')
-        ids =html.xpath('//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()')
-        correct_url = urls[ids.index(number)]
+        # 记录一下欧美的ids  ['Blacked','Blacked']
+        if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number):
+            correct_url = urls[0]
+        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
         imagecut = 3
         # If gray image exists ,then replace with normal cover
-        cover_small = getCover_small(query_result, index=ids.index(number))
+                if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', 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