关注
var keyword = "d3.js";
//@input(keyword, 查询关键字, 爬取该关键字搜索出来的京东商品)
var comment_count = 100;
//@input(comment_count, 爬取的评论数, 最多爬取多少条评论)
var page_count = comment_count / 10;
keyword = keyword.trim();
var scanUrls = [];
scanUrls.push("http://search.jd.com/Search?keyword=" + keyword.replace(/ /g, "+") + "&enc=utf-8&scrolling=y&page=200");
var helperUrlRegexes = [];
helperUrlRegexes.push("http://search\\.jd\\.com/Search\\?keyword=" + keyword.replace(/ /g, "\\+").replace(/\./g, "\\.") + "&enc=utf-8&scrolling=y&page=\\d+");
var configs = {
domains: ["search.jd.com", "item.jd.com", "club.jd.com"], scanUrls: scanUrls, contentUrlRegexes: ["http://item\\.jd\\.com/\\d+.html"], helperUrlRegexes: helperUrlRegexes, interval: 10000, fields: [ { // 第一个抽取项 name: "title", selector: "//div[@id='name']/h1", required: true }, { // 第一个抽取项 name: "productid", selector: "//div[contains(@class,'fl')]/span[2]", required: true }, { name: "comments", selector: "//div[@id='comment-pages']/span", repeated: true, children: [ { name: "page", selector: "//text()" }, { name: "comments", sourceType: SourceType.AttachedUrl, attachedUrl: "http://club.jd.com/productpage/p-{$.productid}-s-0-t-3-p-{page}.html", selectorType: SelectorType.JsonPath, selector: "$.comments", repeated: true, children:[ { name: "com_content", selectorType: SelectorType.JsonPath, selector: "$.content" }, { name: "com_nickname", selectorType: SelectorType.JsonPath, selector: "$.nickname" } ]
} ]
} ]
};
configs.afterDownloadPage = function(page, site) { var matches = /item\.jd\.com\/(\d+)\.html/.exec(page.url);
if (!matches) return page; var commentUrl = "http://club.jd.com/productpage/p-"+matches[1]+"-s-0-t-3-p-0.html";
var result = site.requestUrl(commentUrl);
var data = JSON.parse(result); var commentCount = data.productCommentSummary.commentCount;
var pages = commentCount / 10;
if (pages > page_count) pages = page_count; var pageHtml = "<div id=\"comment-pages\">";
for (var i = 0; i < pages; i++) { pageHtml += "<span>" + i + "</span>"; } pageHtml += "</div>";
var index = page.raw.indexOf("</body>");
page.raw = page.raw.substring(0, index) + pageHtml + page.raw.substring(index); return page; };
var dataSku = 0; configs.onProcessHelperPage = function(page, content, site) { var num = parseInt(extract(content, "//*[@id='J_goodsList']/ul/li[1]/@data-sku"));
if (dataSku === 0) {
dataSku = isNaN(num) ? 0 : num; }
else if (dataSku === num) {
dataSku = 0; return false; } var currentPageNum = parseInt(page.url.substring(page.url.indexOf("&page=") + 6));
if (currentPageNum === 0) {
currentPageNum = 1;
} var pageNum = currentPageNum + 1; var nextUrl = page.url.replace("&page=" + currentPageNum, "&page=" + pageNum);
site.addUrl(nextUrl); return true; };
configs.afterExtractPage = function(page, data) {
if (data.comments === null || data.comments === undefined)
return data; var comments = [];
for (var i = 0; i < data.comments.length; i++) {
var p = data.comments[i]; for (var j = 0; j < p.comments.length; j++) { comments.push(p.comments[j]);
}
}
data.comments = comments;
return data;
};
var crawler = new Crawler(configs); crawler.start();
//牛妹双11快乐,大家双11快乐(*^▽^*)
查看原帖
点赞 3
相关推荐
点赞 评论 收藏
分享
点赞 评论 收藏
分享
牛客热帖
更多
正在热议
更多
# 牛客AI体验站 #
18247次浏览 314人参与
# 记录实习开销 #
185091次浏览 841人参与
# 牛客新年AI问运 #
16047次浏览 173人参与
# 大家每天通勤多久? #
84068次浏览 706人参与
# 正在实习的你,几点下班 #
297508次浏览 2080人参与
# 牛客租房专区 #
154587次浏览 1629人参与
# 不给转正的实习,你还去吗 #
2627514次浏览 22922人参与
# 选择和努力,哪个更重要? #
191442次浏览 1497人参与
# 如何缓解入职前的焦虑 #
259953次浏览 1458人参与
# 我的岗位说明书 #
308154次浏览 2753人参与
# 有转正机会的小厂实习值得去吗? #
1191次浏览 22人参与
# 金融银行求职进展汇总 #
309753次浏览 1686人参与
# 你小时候最想从事什么职业 #
154211次浏览 2059人参与
# 校招入职后的感受 #
488682次浏览 3682人参与
# 入职第一天 #
47656次浏览 554人参与
# 投递无反馈,如何优化求职策略? #
8756次浏览 43人参与
# 工作后会跟朋友渐行渐远吗 #
60313次浏览 415人参与
# 你最讨厌面试被问什么 #
2154次浏览 30人参与
# 牛友们,签完三方你在忙什么? #
137645次浏览 997人参与
# 帆软软件工作体验 #
14727次浏览 86人参与
查看11道真题和解析