fix(novel-crawl): 规则修复

2026-10-16 07:57:30 +08:00
1 parent 25c30ae790
commit b813fbd30c
@@ -0,0 +1,36 @@
+
+INSERT INTO crawl_source (source_name, crawl_rule, source_status, create_time, update_time) VALUES ('书趣阁（2026）', '{
+    "bookListUrl": "http://wap.xshuquge.net/sort/{catId}/0_{page}.html",
+    "catIdRule": {
+        "catId1": "1",
+        "catId2": "2",
+        "catId3": "3",
+        "catId4": "4",
+        "catId5": "7",
+        "catId6": "6",
+        "catId7": "8"
+    },
+    "bookIdPatten": "href=\\"/s/(\\\\d+)\\\\.html\\"",
+    "pagePatten": "第(\\\\d+)/\\\\d+页",
+    "totalPagePatten": "第\\\\d+/(\\\\d+)页",
+    "bookDetailUrl": "http://wap.xshuquge.net/s/{bookId}.html",
+    "bookNamePatten": "<a\\\\s+href=\\"/s/\\\\d+\\\\.html\\"><h2>([^/]+)</h2></a>",
+    "authorNamePatten": "<p>作者：([^/]+)</p>",
+    "picUrlPatten": "src=\\"(http://www.xshuquge.net/files/article/image/\\\\d+/\\\\d+/\\\\d+s\\\\.jpg)\\"",
+    "statusPatten": "<p>状态：([^/]+)</p>",
+    "bookStatusRule": {
+        "连载中": 0,
+        "完本": 1
+    },
+    "descStart": "<div class=\\"intro_info\\">",
+    "descEnd": "最新章节推荐地址",
+    "filterDesc": "",
+    "bookIndexUrl": "http://www.xshuquge.net/txt/{bookId}/index.html",
+    "bookIndexStart": "<dt>《",
+    "indexIdPatten": "<dd><a\\\\s+href=\\"(\\\\d+)\\\\.html\\">[^/]+</a></dd>",
+    "indexNamePatten": "<dd><a\\\\s+href=\\"\\\\d+\\\\.html\\">([^/]+)</a></dd>",
+    "bookContentUrl": "http://www.xshuquge.net/txt/{bookId}/{indexId}.html",
+    "contentStart": "<div id=\\"content\\" class=\\"showtxt\\">",
+    "contentEnd": "http://www.xshuquge.net",
+    "filterContent": "<b>最新网址：www.xshuquge.net</b>"
+}', 1, '2020-05-18 12:02:34', '2026-10-15 17:00:00');
@@ -3248,3 +3248,41 @@ VALUES ('香书小说网（2026）', '{
  "filterContent":"<div\\\\s+id=\\"content_tip\\">\\\\s*<b>([^/]+)</b>\\\\s*</div>"
 }', 0, '2026-10-13 19:22:21', '2026-10-13 19:22:21');

+
+
+INSERT INTO crawl_source (source_name, crawl_rule, source_status, create_time, update_time) VALUES ('书趣阁（2026）', '{
+    "bookListUrl": "http://wap.xshuquge.net/sort/{catId}/0_{page}.html",
+    "catIdRule": {
+        "catId1": "1",
+        "catId2": "2",
+        "catId3": "3",
+        "catId4": "4",
+        "catId5": "7",
+        "catId6": "6",
+        "catId7": "8"
+    },
+    "bookIdPatten": "href=\\"/s/(\\\\d+)\\\\.html\\"",
+    "pagePatten": "第(\\\\d+)/\\\\d+页",
+    "totalPagePatten": "第\\\\d+/(\\\\d+)页",
+    "bookDetailUrl": "http://wap.xshuquge.net/s/{bookId}.html",
+    "bookNamePatten": "<a\\\\s+href=\\"/s/\\\\d+\\\\.html\\"><h2>([^/]+)</h2></a>",
+    "authorNamePatten": "<p>作者：([^/]+)</p>",
+    "picUrlPatten": "src=\\"(http://www.xshuquge.net/files/article/image/\\\\d+/\\\\d+/\\\\d+s\\\\.jpg)\\"",
+    "statusPatten": "<p>状态：([^/]+)</p>",
+    "bookStatusRule": {
+        "连载中": 0,
+        "完本": 1
+    },
+    "descStart": "<div class=\\"intro_info\\">",
+    "descEnd": "最新章节推荐地址",
+    "filterDesc": "",
+    "bookIndexUrl": "http://www.xshuquge.net/txt/{bookId}/index.html",
+    "bookIndexStart": "<dt>《",
+    "indexIdPatten": "<dd><a\\\\s+href=\\"(\\\\d+)\\\\.html\\">[^/]+</a></dd>",
+    "indexNamePatten": "<dd><a\\\\s+href=\\"\\\\d+\\\\.html\\">([^/]+)</a></dd>",
+    "bookContentUrl": "http://www.xshuquge.net/txt/{bookId}/{indexId}.html",
+    "contentStart": "<div id=\\"content\\" class=\\"showtxt\\">",
+    "contentEnd": "http://www.xshuquge.net",
+    "filterContent": "<b>最新网址：www.xshuquge.net</b>"
+}', 1, '2020-05-18 12:02:34', '2026-10-15 17:00:00');
+