HTML/XML parser and web scraper for NodeJS.
Compose deep and complex data structures
HTML parser features
HTML DOM features
HTTP request features
var osmosis = require('osmosis');
osmosis
.get('www.craigslist.org/about/sites')
.find('h1 + div a')
.set('location')
.follow('@href')
.find('header + div + div li > a')
.set('category')
.follow('@href')
.paginate('.totallink + a.button.next:first')
.find('p > a')
.follow('@href')
.set({
'title': 'section > h2',
'description': '#postingbody',
'subcategory': 'div.breadbox > span[4]',
'date': 'time@datetime',
'latitude': '#map@data-latitude',
'longitude': '#map@data-longitude',
'images': ['img@src']
})
.data(function(listing) {
// do something with listing data
})
.log(console.log)
.error(console.log)
.debug(console.log)
For documentation and examples check out https://rchipka.github.com/node-osmosis/
Please consider a donation if you depend on web scraping and Osmosis makes your job a bit easier. Your contribution allows me to spend more time making this the best web scraper for Node.
$ claude mcp add node-osmosis \
-- python -m otcore.mcp_server <graph>