Kiwibp

locations_ten_or_more = all_items_df.groupby(['Location']).filter(lambda g: g.Location.value_counts() >= 10) \
.loc[:,['Location','Description', 'Price', 'Title', 'Url']]

#checking the number of locations with less than 10 items
len_of_locs = len(locations_ten_or_more.groupby("Location").size())
print(f'There are {len_of_locs} cities with 10 items or more.')
print('\n')

#checking the locations with the most items in this subset
print('Locations with the most amount of items in this subset:')

Kiwibp

# -*- coding: utf-8 -*-
import scrapy
import sys

class CraigslistSpider(scrapy.Spider):
    name = 'craigslist'
    allowed_domains = ['asheville.craigslist.org']
    start_urls = ['https://asheville.craigslist.org/search/sss'] 

    def parse(self, response):

Kiwibp

# -*- coding: utf-8 -*-
import scrapy
import json
import requests
import re
from time import sleep
import sys

class LetgoSpider(scrapy.Spider):
    name = 'letgo'

Kiwibp

#pipeline adjustment to export data to MongoDB
from pymongo import MongoClient
from scrapy.conf import settings

class MongoDBPipeline(object):
    def __init__(self):
        connection = MongoClient(
            settings['MONGODB_SERVER'],
            settings['MONGODB_PORT'])