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'])
        

Kiwibp

guards_advanced = urllib.request.urlopen("https://rotogrinders.com/pages/nba-advanced-player-stats-guards-181885").read()
guards_advancedguards_  = bs.BeautifulSoup(guards_advanced, 'lxml')
#leaving out a number of lines necessary to extract data, see github repo for full code if you'd like.
guards_advanced_col_names = col_names.split()
print(guards_advanced_col_names)

#could also use pandas read_html method as well
guards_advanced_dfs = pd.read_html("https://rotogrinders.com/pages/nba-advanced-player-stats-guards-181885")
guards_advanced_stats_df = guards_advanced_dfs[2]
guards_advanced_stats_df.tail()