From db1394dcc4d8bf7066f01f80db80fe8e046e2e19 Mon Sep 17 00:00:00 2001
From: hjdhnx <hjd124579>
Date: Thu, 17 Nov 2022 17:24:50 +0800
Subject: [PATCH] =?UTF-8?q?=E6=B5=8B=E8=AF=95=E6=A1=88=E4=BE=8B=E5=AE=8C?=
 =?UTF-8?q?=E7=BE=8E=E9=80=9A=E8=BF=87?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 js/version.txt                      |  2 +-
 "py/\346\265\213\350\257\225pdf.py" | 10 ++++++----
 utils/htmlParser.py                 | 10 ++++++----
 3 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/js/version.txt b/js/version.txt
index ae94c93..63c0213 100644
--- a/js/version.txt
+++ b/js/version.txt
@@ -1 +1 @@
-3.7.6
\ No newline at end of file
+3.7.5beta10
\ No newline at end of file
diff --git "a/py/\346\265\213\350\257\225pdf.py" "b/py/\346\265\213\350\257\225pdf.py"
index 9ad060f..04386f9 100644
--- "a/py/\346\265\213\350\257\225pdf.py"
+++ "b/py/\346\265\213\350\257\225pdf.py"
@@ -29,8 +29,10 @@ def main():
     print(a)
     a = jsp.pdfh(lis[0], 'a:eq(1) li img')
     print(a)
-    a = jsp.pd(lis[0], 'a&&li&&img&&src')
-    print(a)
+    a = jsp.pd(lis[0], 'a:eq(1)&&li&&img&&src')
+    print('src:',a)
+    a = jsp.pd(lis[0], 'a&&href')
+    print('href:', a)
 
 def main1():
     url = 'https://www.lanhua.tv/voddetail/7420.html'
@@ -89,7 +91,7 @@ def main3():
     print(a)
 
 if __name__ == '__main__':
-    # main()
+    main()
     # main1()
     # main2()
-    main3()
\ No newline at end of file
+    # main3()
\ No newline at end of file
diff --git a/utils/htmlParser.py b/utils/htmlParser.py
index 9bf4fdb..0f028f2 100644
--- a/utils/htmlParser.py
+++ b/utils/htmlParser.py
@@ -160,7 +160,7 @@ class jsoup:
         res = [item.outerHtml() for item in ret.items()]
         return res
 
-    def pdfh(self, html, parse: str, add_url=False):
+    def pdfh(self, html, parse: str, add_url=False, base_url: str = ''):
         if not all([html, parse]):
             return ''
         if PARSE_CACHE:
@@ -210,13 +210,15 @@ class jsoup:
                         if 'http' in ret:
                             ret = ret[ret.find('http'):]
                         else:
-                            ret = urljoin(self.MY_URL, ret)
+                            if not base_url:
+                                base_url = self.MY_URL
+                            ret = urljoin(base_url, ret)
         else:
             ret = ret.outerHtml()
         return ret
 
-    def pd(self, html, parse: str):
-        return self.pdfh(html, parse, True)
+    def pd(self, html, parse: str, base_url: str = ''):
+        return self.pdfh(html, parse, True, base_url)
 
     def pq(self, html: str):
         return pq(html)
-- 
GitLab