fix(novel-crawl): 修复爬虫规则

This commit is contained in:
xiongxiaoyang committed 2026-10-13 20:06:43 +08:00
1 parent 3a3a8a38a4
commit 11b7b46c42
2 files changed
+67 -1

No files matched your search

+32
View File
@@ -0,0 +1,32 @@
INSERT INTO crawl_source (source_name, crawl_rule, source_status, create_time, update_time)
VALUES ('香书小说网(2026)', '{
"bookListUrl": "http://www.ibiqugu.net/fenlei/{catId}_{page}.html",
"catIdRule": {
"catId1": "1",
"catId2": "2",
"catId3": "3",
"catId4": "4",
"catId5": "6",
"catId6": "5"
},
"bookIdPatten": "<a\\\\s+href=\\"http://www.ibiqugu.net/(\\\\d+/\\\\d+)/\\"\\\\s+target=\\"_blank\\">",
"pagePatten": "<em\\\\s+id=\\"pagestats\\">(\\\\d+)/\\\\d+</em>",
"totalPagePatten": "<em\\\\s+id=\\"pagestats\\">\\\\d+/(\\\\d+)</em>",
"bookDetailUrl": "http://www.ibiqugu.net/{bookId}/",
"bookNamePatten": "<h1>([^/]+)</h1>",
"authorNamePatten": "者:([^/]+)</p>",
"picUrlPatten": "src=\\"(http://www.ibiqugu.net/files/article/image/\\\\d+/\\\\d+/\\\\d+s\\\\.jpg)\\"",
"bookStatusRule": {},
"descStart": "<div id=\\"intro\\">",
"descEnd": "</div>",
"upadateTimePatten": "<p>最后更新:(\\\\d+-\\\\d+-\\\\d+\\\\s\\\\d+:\\\\d+:\\\\d+)</p>",
"upadateTimeFormatPatten": "yyyy-MM-dd HH:mm:ss",
"bookIndexUrl": "http://www.ibiqugu.net/{bookId}/",
"indexIdPatten": "<a\\\\s+href=''/\\\\d+/\\\\d+/(\\\\d+)\\\\.html''\\\\s+>[^/]+</a>",
"indexNamePatten": "<a\\\\s+href=''/\\\\d+/\\\\d+/\\\\d+\\\\.html''\\\\s+>([^/]+)</a>",
"bookContentUrl": "http://www.ibiqugu.net/{bookId}/{indexId}.html",
"contentStart": "<div id=\\"content\\">",
"contentEnd": "<p>",
"filterContent":"<div\\\\s+id=\\"content_tip\\">\\\\s*<b>([^/]+)</b>\\\\s*</div>"
}', 0, '2026-10-13 19:22:21', '2026-10-13 19:22:21');
+35 -1
View File
@@ -3213,4 +3213,38 @@ VALUES ('飘天文学网(海外专用)', '{
"filterContent": "",
"charset": "gbk"
}', 0, '2025-07-13 18:57:39'
, '2025-07-13 18:57:39');
, '2025-07-13 18:57:39');
INSERT INTO crawl_source (source_name, crawl_rule, source_status, create_time, update_time)
VALUES ('香书小说网(2026)', '{
"bookListUrl": "http://www.ibiqugu.net/fenlei/{catId}_{page}.html",
"catIdRule": {
"catId1": "1",
"catId2": "2",
"catId3": "3",
"catId4": "4",
"catId5": "6",
"catId6": "5"
},
"bookIdPatten": "<a\\\\s+href=\\"http://www.ibiqugu.net/(\\\\d+/\\\\d+)/\\"\\\\s+target=\\"_blank\\">",
"pagePatten": "<em\\\\s+id=\\"pagestats\\">(\\\\d+)/\\\\d+</em>",
"totalPagePatten": "<em\\\\s+id=\\"pagestats\\">\\\\d+/(\\\\d+)</em>",
"bookDetailUrl": "http://www.ibiqugu.net/{bookId}/",
"bookNamePatten": "<h1>([^/]+)</h1>",
"authorNamePatten": "者:([^/]+)</p>",
"picUrlPatten": "src=\\"(http://www.ibiqugu.net/files/article/image/\\\\d+/\\\\d+/\\\\d+s\\\\.jpg)\\"",
"bookStatusRule": {},
"descStart": "<div id=\\"intro\\">",
"descEnd": "</div>",
"upadateTimePatten": "<p>最后更新:(\\\\d+-\\\\d+-\\\\d+\\\\s\\\\d+:\\\\d+:\\\\d+)</p>",
"upadateTimeFormatPatten": "yyyy-MM-dd HH:mm:ss",
"bookIndexUrl": "http://www.ibiqugu.net/{bookId}/",
"indexIdPatten": "<a\\\\s+href=''/\\\\d+/\\\\d+/(\\\\d+)\\\\.html''\\\\s+>[^/]+</a>",
"indexNamePatten": "<a\\\\s+href=''/\\\\d+/\\\\d+/\\\\d+\\\\.html''\\\\s+>([^/]+)</a>",
"bookContentUrl": "http://www.ibiqugu.net/{bookId}/{indexId}.html",
"contentStart": "<div id=\\"content\\">",
"contentEnd": "<p>",
"filterContent":"<div\\\\s+id=\\"content_tip\\">\\\\s*<b>([^/]+)</b>\\\\s*</div>"
}', 0, '2026-10-13 19:22:21', '2026-10-13 19:22:21');