You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
55 lines
1.3 KiB
JavaScript
55 lines
1.3 KiB
JavaScript
#!/usr/bin/env node
|
|
/* eslint-disable */
|
|
|
|
const Mercury = require('./dist/mercury');
|
|
const argv = require('yargs-parser')(process.argv.slice(2));
|
|
|
|
const {
|
|
_: [url],
|
|
format,
|
|
f,
|
|
} = argv;
|
|
(async (urlToParse, contentType) => {
|
|
if (!urlToParse) {
|
|
console.log(
|
|
'\n\
|
|
mercury-parser\n\n\
|
|
The Mercury Parser extracts semantic content from any url\n\n\
|
|
Usage:\n\
|
|
\n\
|
|
$ mercury-parser url-to-parse [--format=html|text|markdown]\n\
|
|
\n\
|
|
'
|
|
);
|
|
return;
|
|
}
|
|
try {
|
|
const contentTypeMap = {
|
|
html: 'html',
|
|
markdown: 'markdown',
|
|
md: 'markdown',
|
|
text: 'text',
|
|
txt: 'text',
|
|
};
|
|
const result = await Mercury.parse(urlToParse, null, {
|
|
contentType: contentTypeMap[contentType],
|
|
});
|
|
console.log(JSON.stringify(result, null, 2));
|
|
} catch (e) {
|
|
if (e.message === 'ETIMEDOUT' && false) {
|
|
console.error(
|
|
'\nMercury Parser encountered a timeout trying to load that resource.'
|
|
);
|
|
} else {
|
|
console.error(
|
|
'\nMercury Parser encountered a problem trying to parse that resource.\n'
|
|
);
|
|
console.error(e);
|
|
}
|
|
const reportBug =
|
|
'If you believe this was an error, please file an issue at:\n\n https://github.com/postlight/mercury-parser/issues/new';
|
|
console.error(`\n${reportBug}\n`);
|
|
process.exit(1);
|
|
}
|
|
})(url, format || f);
|