example scraper code for NICAR 2020

scraper.py

import requests
import bs4
import csv

URL = 'http://www.dllr.state.md.us/employment/warn.shtml'
warn_page = requests.get(URL)

soup = bs4.BeautifulSoup(warn_page.text, 'html.parser')
table = soup.find('table')
rows = table.find_all('tr')

HEADERS = ['warn_date', 'naics_code', 'biz', 'address', 'wia_code', 'total_employees', 'effective_date', 'type_code']

with open('warn-data.csv', 'w', newline='') as outfile:
    writer = csv.writer(outfile)
    writer.writerow(HEADERS)

    for row in rows[1:]:
        cells = row.find_all('td')
        warn_date = cells[0].text.strip()
        naics_code = cells[1].text.strip()
        biz = cells[2].text.strip().split()
        clean_biz = ' '.join(biz)
        address = cells[3].text.strip().split()
        clean_address = ' '.join(address)
        wia_code = cells[4].text.strip()
        total_employees = cells[5].text.strip()
        effective_date = cells[6].text.strip()
        type_code = cells[7].text.strip()

        data_out = [warn_date, naics_code, clean_biz, clean_address, wia_code, total_employees, effective_date, type_code]
        writer.writerow(data_out)

https://raw.githubusercontent.com/ireapps/teaching-guide-python-scraping/master/mlb.html

http://www.dllr.state.md.us/employment/warn.shtml