- Default http://quotes.toscrape.com/
- Scroll http://quotes.toscrape.com/scroll
- JavaScript http://quotes.toscrape.com/js
- Tableful http://quotes.toscrape.com/tableful
- None
- Login http://quotes.toscrape.com/login
- ViewState http://quotes.toscrape.com/search.aspx
- None
- Random http://quotes.toscrape.com/random
- quotes_random
yield response.follow(next_page, self.parse, dont_filter=True)
db.quotestoscrape.aggregate([
{$group: {_id: {text: '$text', author: '$author'}, count: {$sum: 1}, dups: {$addToSet: '$_id'}}},
{$match: {count: {$gt: 1}}}
]).forEach(function(doc){
doc.dups.shift();
db.quotestoscrape.remove({_id: {$in: doc.dups}});
})
db.quotestoscrape.aggregate([
{$group: {_id : '$text', count: {$sum : 1}}},
{$match: {count: {$gt : 1}}}
])