Question

我试图抓取谷歌新闻，但我使用的代码有问题：

 var express = require('express');
var request = require('request');
var cheerio = require('cheerio');
var path = require('path');
var fs =require('fs');
var app = express();
var port = 8080;


 // Define the requests url

 var url = "https://news.google.com/news";

request(url,function(err,res,body){

var news=[];
 var $page = cheerio.load(body);

var $url=$page('table[class="esc-layout-table"]').find('tbody > tr > td > div > h2 > a').each(function (index, element) {
  news.push($page(element).attr('href'));
});
news={
//desc:$desc,
    url:$url,
//    img:$img,
};



console.log ('success ....'news);



});

我想要链接到文章和标题以及缩略图。我将存储在firebase数据库中但不幸的是我在其余的控制台日志中迷路了我不能得到我期望的结果而不是我在控制台中得到这个：

    success .... { '0':
   { type: 'tag',
     name: 'a',
     attribs:
      { target: '_blank',
        class: 'article usg-AFQjCNFxodYTzKo8-hM57511iQgBdfn8xA did-3230940966728164415',
        href: 'https://www.washingtonpost.com/news/post-nation/wp/2016/12/15/jurors-begin-deliberating-in-charleston-church-shooting-trial/',
        url: 'https://www.washingtonpost.com/news/post-nation/wp/2016/12/15/jurors-begin-deliberating-in-charleston-church-shooting-trial/',
        id: 'MAA4AEgAUABgAWoCdXM',
        ssid: 'h' },
     children: [ [Object] ],
     next: null,
     prev: null,
     parent:
      { type: 'tag',
        name: 'h2',
        attribs: [Object],
        children: [Object],
        next: null,
        prev: null,
        parent: [Object] } },
  '1':
   { type: 'tag',
     name: 'a',
     attribs:
      { target: '_blank',
        class: 'article usg-AFQjCNEQY4otecPJJevDyoBp3K-IQnes2w did-141563424311867977',
        href: 'http://www.businessinsider.com/facebook-will-fact-check-label-fake-news-in-news-feed-2016-12',
        url: 'http://www.businessinsider.com/facebook-will-fact-check-label-fake-news-in-news-feed-2016-12',
        id: 'MAA4AEgBUABgAWoCdXM',
        ssid: 'h' },
     children: [ [Object] ],
     next: null,
     prev: null,
     parent:
      { type: 'tag',
        name: 'h2',
        attribs: [Object],
        children: [Object],
        next: null,
        prev: null,
        parent: [Object] } },
  '2':
   { type: 'tag',
     name: 'a',
     attribs:
      { target: '_blank',
        class: 'article usg-AFQjCNHyGG4zl4RW-AoIILTssJX_TKCybg did--2293954291931624250',
        href: 'http://www.bbc.com/news/world-middle-east-38329461',
        url: 'http://www.bbc.com/news/world-middle-east-38329461',
        id: 'MAA4AEgCUABgAWoCdXM',
        ssid: 'h' },
     children: [ [Object] ],
     next: null,
     prev: null,
     parent:
      { type: 'tag',
        name: 'h2',
        attribs: [Object],
        children: [Object],
        next: null,
        prev: null,
        parent: [Object] } },
  '3':

注意：如果您运行代码，这只是结果中的一小部分，您将清楚地看到我的意思谢谢你的建议。

Answer 1

不确定这是你想要的但是试试这个我得到了你想要的所有网址

 var express = require('express');
var request = require('request');
var cheerio = require('cheerio');
var path = require('path');
var fs =require('fs');
var app = express();
var port = 8080;


 // Define the requests url

 var url = "https://news.google.com/news";

request(url,function(err,res,body){

var news=[];

var $= cheerio.load(body);

$('table[class="esc-layout-table"]').each(function () {
  var image = $(this).find('tbody > tr > .esc-layout-thumbnail-cell > .esc-thumbnail-wrapper > .esc-thumbnail-state > .esc-thumbnail > a > .esc-thumbnail-image-wrapper > img').attr('src');
  var title = $(this).find('tbody > tr > .esc-layout-article-cell > .esc-lead-article-title-wrapper > .esc-lead-article-title > a > span').text();
  var url = $(this).find('tbody > tr > .esc-layout-article-cell > .esc-lead-article-title-wrapper > .esc-lead-article-title > a').attr('href');
  news.push({ url, title, image });
});


console.log ('success ....', news);



});

结果

success .... [ { url: 'http://www.cbc.ca/news/canada/saskatchewan/prisoner-killed-sask-penitentiary-1.3898175',
    title: '1 dead, at least 8 injured in Saskatchewan prison riot',
    image: '//t2.gstatic.com/images?q=tbn:ANd9GcRKhvczSgL4g3dO8EHkruAEB5AoqkI-PvbB8LzlHBZTPGJYh4bEooNKApDXqTzboNrLpqv3H7MG' },
  { url: 'http://www.cbc.ca/news/world/aleppo-convoy-evacuation-1.3895602',
    title: '3000 people evacuated from eastern Aleppo so far as fragile ceasefire holds',
    image: '//t2.gstatic.com/images?q=tbn:ANd9GcQ86WfdQJVFE4GrQvu_CPrjx3sqhqut0gjBRv6opfVA4JLIqsWeBDjRWURFGd7h_XN_0D0DnoQ5' },
  { url: 'http://www.cp24.com/news/five-family-members-dead-following-first-nation-fire-1.3204960',
    title: 'Five family members dead following First Nation fire',
    image: '//t1.gstatic.com/images?q=tbn:ANd9GcS6DkmtVrLs4wzVLDfNZvfOm9Js6rXvSg8ttjdoofJwWUZkM2wSjvLA-HpVZdTJN7pG-1FubXI' },
  { url: 'http://www.ctvnews.ca/business/b-c-offers-five-year-interest-free-down-payment-loans-to-first-time-buyers-1.3205119',
    title: 'BC offers five-year, interest-free down-payment loans to first-time buyers',
    image: '//t3.gstatic.com/images?q=tbn:ANd9GcR2gUEW4E0gtt5Sj-jFIJP0iC1JIIZ3qi5RbpbwD7otN7B5nKf8qXT-Q1Aaxcs5Z7FVn-LhNXU5' },

希望能帮助你：）

刮刮谷歌新闻

1 个答案: