From 41972dec8eda1e681b0eef81bc35c7ffd54e80ac Mon Sep 17 00:00:00 2001
From: hjdhnx <hjd124579>
Date: Wed, 16 Nov 2022 14:30:50 +0800
Subject: [PATCH] =?UTF-8?q?js0=20pdfh=E4=BF=AE=E6=AD=A3?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 base/rules.db       | Bin 155648 -> 155648 bytes
 js/version.txt      |   2 +-
 utils/htmlParser.py |   7 ++++++-
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/base/rules.db b/base/rules.db
index e671074eb342cab903708e871ce0a3f8e487b4b9..47af86169616a5dcea3631bbe6b2031d5bcc3545 100644
GIT binary patch
delta 25
hcmZoTz}awsbAmMEtcfztjI$aOS`!$zCNM3C2LO8^2|)k=

delta 25
hcmZoTz}awsbAmMEjEOSNj58V&S`!$zCNM3C2LO8O2|WM+

diff --git a/js/version.txt b/js/version.txt
index dcd32c1..00e897b 100644
--- a/js/version.txt
+++ b/js/version.txt
@@ -1 +1 @@
-3.8.3
\ No newline at end of file
+3.8.2
\ No newline at end of file
diff --git a/utils/htmlParser.py b/utils/htmlParser.py
index b1df739..23ac23e 100644
--- a/utils/htmlParser.py
+++ b/utils/htmlParser.py
@@ -11,7 +11,7 @@ import re
 from jsonpath import jsonpath
 
 PARSE_CACHE = True  # 解析缓存
-NOADD_INDEX = ':eq|:lt|:gt|^body$|^#'  # 不自动加eq下标索引
+NOADD_INDEX = ':eq|:lt|:gt|:first|:last|^body$|^#'  # 不自动加eq下标索引
 URLJOIN_ATTR = '(url|src|href|-original|-src|-play|-url)$'  # 需要自动urljoin的属性
 
 
@@ -134,6 +134,11 @@ class jsoup:
                 else:
                     new_parses.append(parse[i])
             parse = ' '.join(new_parses)
+        else:
+            ps = parse.split(' ')[-1]  # 如果带空格就取最后一个元素
+            if not self.test(NOADD_INDEX, ps) and first:
+                parse = f'{parse}:eq(0)'
+
         return parse
 
     def pdfa(self, html, parse: str):
-- 
GitLab