测试案例完美通过

js/version.txt

-3.7.6
\ No newline at end of file
+3.7.5beta10
\ No newline at end of file

py/测试pdf.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

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)