优化了pd系列函数

js/version.txt

-3.7.5beta10
\ No newline at end of file
+3.7.5beta9
\ No newline at end of file

libs/drpy2.js

@@ -425,47 +425,7 @@ var urljoin2 = urljoin;
 const defaultParser = {
     pdfh:pdfh,
     pdfa:pdfa,
-    parseHikerToJq(parse,first){
-        // 海阔解析表达式转原生表达式,自动补eq,如果传了first就最后一个也取eq(0)
-        first = first||false;
-        if(parse.includes('&&')){
-            parse = parse.split('&&');  //带&&的重新拼接
-            let new_parses = [];  // 构造新的解析表达式列表
-            parse.forEach((it,i)=>{
-                let ps = it.split(' ').slice(-1)[0];  // 如果分割&&后带空格就取最后一个元素
-                if(!NOADD_INDEX.test(ps)){
-                    if(!first&&i>=parse.length-1){
-                        new_parses.push(it);
-                    }else{
-                        new_parses.push(`${it}:eq(0)`);
-                    }
-                }else{
-                    new_parses.push(it);
-                }
-            });
-            parse = new_parses.join(' ');
-        }else{
-            let ps = parse.split(' ').slice(-1)[0];  // 如果带空格就取最后一个元素
-            if(!NOADD_INDEX.test(ps) && first){
-                parse = `${parse}:eq(0)`;
-            }
-        }
-        return parse;
-    },
-    pd(html,parse,uri){
-        let ret = this.pdfh(html,parse);
-        if(typeof(uri)==='undefined'||!uri){
-            uri = '';
-        }
-        if(DOM_CHECK_ATTR.test(parse)){
-            if(/http/.test(ret)){
-                ret = ret.substr(ret.indexOf('http'));
-            }else{
-                ret = urljoin(MY_URL,ret)
-            }
-        }
-        return ret
-    },
+    pd:pd,
 };
 
 
@@ -599,36 +559,13 @@ const parseTags = {
         },
     },
     jq:{
-        pdfh(html, parse, base_url) {
+        pdfh(html, parse) {
             if (!html||!parse || !parse.trim()) {
                 return ''
             }
             parse = parse.trim();
-            let reparse = ['body&&Text','Text','body&&Html','Html'];
-            if(reparse.includes(reparse)){
-                return defaultParser.pdfh(html,parse)
-            }
-            let option = '';
-            if(parse.includes('&&')){
-                option = parse.split('&&').slice(-1)[0];
-                parse =  parse.split('&&').slice(0,-1).join('&&');
-            }
-            parse = defaultParser.parseHikerToJq(parse, true);
-            let result = defaultParser.pdfh(html,parse,option);
-            if(option&&/style/.test(option.toLowerCase())&&/url\(/.test(result)){
-                try {
-                    result =  result.match(/url\((.*?)\)/)[1];
-                    // print(result);
-                }catch (e) {}
-            }
-            if (result && base_url && option && DOM_CHECK_ATTR.test(option)) {
-                if (/http/.test(result)) {
-                    result = result.substr(result.indexOf('http'));
-                } else {
-                    result = urljoin(base_url, result)
-                }
-                // print(result);
-            }
+            let result = defaultParser.pdfh(html,parse);
+            // print(`pdfh解析${parse}=>${result}`);
             return result;
         },
         pdfa(html, parse) {
@@ -636,14 +573,18 @@ const parseTags = {
                 return [];
             }
             parse = parse.trim();
-            parse = defaultParser.parseHikerToJq(parse)
             let result = defaultParser.pdfa(html,parse);
             // print(result);
             print(`pdfa解析${parse}=>${result.length}`);
             return result;
         },
-        pd(html,parse,uri){
-            return parseTags.jq.pdfh(html, parse, MY_URL);
+        pd(html,parse,base_url){
+            if (!html||!parse || !parse.trim()) {
+                return ''
+            }
+            parse = parse.trim();
+            base_url = base_url||MY_URL;
+            return defaultParser.pd(html, parse, base_url);
         },
     },
     getParse(p0){//非js开头的情况自动获取解析标签

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, base_url: str = ''):
+    def pdfh(self, html, parse: str, base_url: str = ''):
         if not all([html, parse]):
             return ''
         if PARSE_CACHE:
@@ -204,21 +204,21 @@ class jsoup:
                     except:
                         pass
 
-                if ret and add_url:
+                if ret and base_url:
                     need_add = re.search(URLJOIN_ATTR, option, re.M | re.I)
                     if need_add:
                         if 'http' in ret:
                             ret = ret[ret.find('http'):]
                         else:
-                            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, base_url: str = ''):
-        return self.pdfh(html, parse, True, base_url)
+        if not base_url:
+            base_url = self.MY_URL
+        return self.pdfh(html, parse, base_url)
 
     def pq(self, html: str):
         return pq(html)