项目地址：smuyyh/CrawlerForReader
简介：Android 本地网络小说爬虫，基于 jsoup 及 xpath
更多：作者提 Bug
标签：
Android 本地网络小说爬虫，基于 jsoup 与 xpath，通过模版解析网页。
支持书源
模版示例
调用方式
ScreenShot
支持书源
/**
所有书源
*/
public static final SparseArray SOURCES = new SparseArray() {
{
put(SourceID.LIEWEN, new Source(SourceID.LIEWEN, “猎文网”, “/search.php?keyword=%s”));
put(SourceID.CHINESE81, new Source(SourceID.CHINESE81, “八一中文网”, “/search.php?keyword=%s”));
put(SourceID.ZHUISHU, new Source(SourceID.ZHUISHU, “追书网”, “https://www.zhuishu.tw/search.aspx?keyword=%s”));
put(SourceID.BIQUG, new Source(SourceID.BIQUG, “笔趣阁”, “/cse/search?s=1393206249994657467&q=%s”));
put(SourceID.WENXUEMI, new Source(SourceID.WENXUEMI, “文学迷”, “/search.php?keyword=%s”));
put(SourceID.CHINESEXIAOSHUO, new Source(SourceID.CHINESEXIAOSHUO, “小说中文网”, “/s.php?ie=gbk&s=10385337132858012269&q=%s”));
put(SourceID.DINGDIAN, new Source(SourceID.DINGDIAN, “顶点小说”, “/cse/search?s=1682272515249779940&q=%s”));
put(SourceID.BIQUGER, new Source(SourceID.BIQUGER, “笔趣阁 2”, “/cse/search?s=7928441616248544648&ie=utf-8&q=%s”));
put(SourceID.CHINESEZHUOBI, new Source(SourceID.CHINESEZHUOBI, “着笔中文网”, “/s.php?ie=utf-8&s=4619765769851182557&q=%s”));
put(SourceID.DASHUBAO, new Source(SourceID.DASHUBAO, “大书包”, “/cse/search?s=9410583021346449776&entry=1&ie=utf-8&q=%s”));
put(SourceID.CHINESEWUZHOU, new Source(SourceID.CHINESEWUZHOU, “梧州中文台”, “/search.htm?keyword=%s”));
put(SourceID.UCSHUMENG, new Source(SourceID.UCSHUMENG, “UC 书盟”, “/modules/article/search.php?searchkey=%s”, 4));
put(SourceID.QUANXI
《Android学习笔记总结+最新移动架构视频+大厂安卓面试真题+项目实战源码讲义》
【/doc/DSkNLaERkbnFoS0ZF】 完整内容开源分享
AOSHUO, new Source(SourceID.QUANXIAOSHUO, “全小说”, “http://qxs.la/s_%s”));
put(SourceID.YANMOXUAN, new Source(SourceID.YANMOXUAN, “衍墨轩”, “/search.htm?keyword=%s”));
put(SourceID.AIQIWENXUE, new Source(SourceID.AIQIWENXUE, “爱奇文学”, “/?m=book/search&keyword=%s”));
put(SourceID.QIANQIANXIAOSHUO, new Source(SourceID.QIANQIANXIAOSHUO, “千千小说”, “/modules/article/search.php?searchkey=%s”, 4));
put(SourceID.PIAOTIANWENXUE, new Source(SourceID.PIAOTIANWENXUE, “飘天文学网”, “/modules/article/search.php?searchtype=articlename&searchkey=%s”));
put(SourceID.SUIMENGXIAOSHUO, new Source(SourceID.SUIMENGXIAOSHUO, “随梦小说网”, “http://m.suimeng.la/modules/article/search.php?searchkey=%s”, 4));
put(SourceID.DAJIADUSHUYUAN, new Source(SourceID.DAJIADUSHUYUAN, “大家读书苑”, “/modules/article/searchab.php?searchkey=%s”));
put(SourceID.SHUQIBA, new Source(SourceID.SHUQIBA, “书旗吧”, “/modules/article/search.php?searchkey=%s”, 4));
put(SourceID.XIAOSHUO52, new Source(SourceID.XIAOSHUO52, “小说 52”, “/search.php?searchkey=%s”));
}
};
模版示例
例如针对猎文网：
{
“id”: 1, //对应书源 id
“search”: { //搜索页解析规则
“charset”: “UTF-8”,
“xpath”: “//div[@class=‘result-item result-game-item’]”,
“coverXpath”: “//div[@class=‘result-game-item-pic’]//a//img/@src”,
“titleXpath”: “//div[@class=‘result-game-item-detail’]//h3//a/@title”,
“linkXpath”: “//div[@class=‘result-game-item-detail’]//h3//a/@href”,
“authorXpath”: “//div[@class=‘result-game-item-detail’]//div[@class=‘result-game-item-info’]//p[1]/span[2]/text()”,
“descXpath”: “//div[@class=‘result-game-item-detail’]//p[@class=‘result-game-item-desc’]/text()”
},
“catalog”: { //目录列表解析规则
“xpath”: “//div[@id=list]//dl//dd”,
“titleXpath”: “//a/text()”,
“linkXpath”: “//a/@href”
},
“content”: { //文章内容解析规则
“xpath”: “//div[@id=‘content’]/text()”
}
}
调用方式
目前虽然请求结果是通过 Callback 形式，因为搜多个源是分批返回结果。内部当仍是同步请求，没有做线程调度。
},
“content”: { //文章内容解析规则
“xpath”: “//div[@id=‘content’]/text()”
}
}
调用方式
目前虽然请求结果是通过 Callback 形式，因为搜多个源是分批返回结果。内部当仍是同步请求，没有做线程调度。
