From 82315472f66794f5f9c21537f94ec27e3bb2b403 Mon Sep 17 00:00:00 2001
From: Yoshiko2 <42309414+yoshiko2@users.noreply.github.com>
Date: Fri, 17 Jul 2020 15:06:42 +0800
Subject: [PATCH] Upate 3.5.1

---
 config.py        |  6 +++++-
 javdb.py         | 19 ++++++++++++++-----
 number_parser.py |  2 +-
 test.py          |  5 +++++
 4 files changed, 25 insertions(+), 7 deletions(-)
 create mode 100644 test.py

diff --git a/config.py b/config.py
index bdbebe0..b912477 100644
--- a/config.py
+++ b/config.py
@@ -1,12 +1,16 @@
 import os
 import configparser
+import codecs
 
 
 class Config:
     def __init__(self, path: str = "config.ini"):
         if os.path.exists(path):
             self.conf = configparser.ConfigParser()
-            self.conf.read(path, encoding="utf-8")
+            try:
+                self.conf.read(path, encoding="utf-8-sig")
+            except:
+                self.conf.read(path, encoding="utf-8")
         else:
             print("[-] Config file not found! Use the default settings")
             self.conf = self._default_config()
diff --git a/javdb.py b/javdb.py
index ce19601..6a0ccbd 100755
--- a/javdb.py
+++ b/javdb.py
@@ -68,13 +68,22 @@ def getCover_small(a, index=0):
     # javdb sometime returns multiple results
     # DO NOT just get the firt one, get the one with correct index number
     html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@src")[index]
-    if not 'https' in result:
-        result = 'https:' + result
-    return result
+    try:
+        result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@src")[index]
+        if not 'https' in result:
+            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
 def getCover(htmlcode):
     html = etree.fromstring(htmlcode, etree.HTMLParser())
-    result = str(html.xpath("//div[contains(@class, 'column-video-cover')]/a/img/@src")).strip(" ['']")
+    try:
+        result = html.xpath("//div[contains(@class, 'column-video-cover')]/a/img/@src")[0]
+    except: # 2020.7.17 Repair Cover Url crawl
+        result = html.xpath("//div[contains(@class, 'column-video-cover')]/img/@src")[0]
     return result
 def getDirector(a):
     html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
diff --git a/number_parser.py b/number_parser.py
index bbbbe0d..d9e35f8 100644
--- a/number_parser.py
+++ b/number_parser.py
@@ -45,4 +45,4 @@ def get_number(filepath: str) -> str:
 
 if __name__ == "__main__":
     import doctest
-    doctest.testmod(raise_on_error=True)
+    doctest.testmod(raise_on_error=True)
\ No newline at end of file
diff --git a/test.py b/test.py
new file mode 100644
index 0000000..930541c
--- /dev/null
+++ b/test.py
@@ -0,0 +1,5 @@
+## 2020.6.22 更新
+* 改进：网站爬虫子程序参数混乱
+* 修复：命名规则release参数带```/```的问题
+* 新增：socks5本地代理连接
+* 新增：命名规则series参数
\ No newline at end of file