Created
February 15, 2015 05:20
-
-
Save kielni/0c6d921d68cfcef85068 to your computer and use it in GitHub Desktop.
Extract title and description of City of San Jose camp from URL and append to a text file
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| var request = require("request"), | |
| cheerio = require("cheerio"), | |
| _ = require("lodash"), | |
| fs = require("fs"), | |
| readline = require("readline"); | |
| var rl = readline.createInterface(process.stdin, process.stdout); | |
| rl.setPrompt('url> '); | |
| rl.prompt(''); | |
| rl.on('line', function(line) { | |
| rl.prompt(); | |
| var url = line.trim(); | |
| request(url, function(err, response, body) { | |
| if (err) throw err; | |
| var $ = cheerio.load(body); | |
| var title = $('title').text().trim(); | |
| var p = ["","","","","",""]; | |
| $(".an-overlay-leftinfo p").each(function(idx, element) { | |
| p[idx] = $(element).text().trim(); | |
| }); | |
| // description is in 5th 0-indexed p; if not there, the 2nd | |
| var descIdx = _.find([4,1], function(idx) { | |
| return p[idx].length > 80; | |
| }); | |
| var desc = p[descIdx]; | |
| // unless it's somewhere else | |
| var text = $(".overlay-description-text").text().trim(); | |
| if (!desc && text.length > 0) { | |
| desc = text; | |
| } | |
| var camp = "\n"+url+"\n"+title+"\n"+desc+"\n"; | |
| fs.appendFile("san_jose.txt", camp, function (err) { | |
| console.log("camp: "+title+"\n---\n"+desc+"\n\n"); | |
| rl.prompt(''); | |
| }); | |
| }); | |
| }).on('close', function() { | |
| process.exit(0); | |
| }); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment