Created
October 7, 2016 07:00
-
-
Save ssddi456/4c62fcc9d7203df5681eefc3aad6929f to your computer and use it in GitHub Desktop.
for grab noval from xs.dmzj
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 clawer_aggregate = require('./..'); | |
| var commander = require('commander'); | |
| var fs = require('fs'); | |
| var path = require('path'); | |
| program = commander | |
| .usage('') | |
| .option('--chapture <url>', 'page url') | |
| .option('--noval <url>', 'noval url') | |
| .parse(process.argv); | |
| if( !program.noval && !program.chapture ){ | |
| program.help() | |
| } else if( program.noval ){ | |
| clawer_aggregate({ | |
| }) | |
| .grep( program.noval, { | |
| title : ['text', 'h1'], | |
| content: ['href', '.wrapper .left .download_boxbg a:first-of-type'] | |
| }) | |
| .unwind('content') | |
| .grep('$content', { | |
| doc : 'content' | |
| }) | |
| .exec(function(e, res ) { | |
| if( e ){ | |
| console.log( e.stack ); | |
| } else { | |
| var filename= path.join(__dirname, res[0].title + '.txt'); | |
| res.forEach(function( doc ) { | |
| fs.appendFileSync( filename, doc.doc ); | |
| }); | |
| console.log('all done', filename); | |
| } | |
| }) | |
| } else if( program.chapture ){ | |
| clawer_aggregate({}) | |
| .grep(program.chapture, { | |
| title : ['text', 'h1'], | |
| content : ['text', '#novel_contents.novel_text'] | |
| }) | |
| .exec(function( e ) { | |
| if( e ){ | |
| console.log( e.stack ); | |
| } else { | |
| var filename= path.join(__dirname, res[0].title + '.txt'); | |
| res.forEach(function( doc ) { | |
| fs.appendFileSync( filename, doc.doc ); | |
| }); | |
| console.log('all done', filename); | |
| } | |
| }); | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment