Last active
May 4, 2020 03:15
-
-
Save TrevorMcCormick/3e08890b8a74846b55bc847c54cda38c to your computer and use it in GitHub Desktop.
Cosmetology Scrape
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#Import packages | |
import requests | |
from bs4 import BeautifulSoup | |
import pandas as pd | |
df = pd.DataFrame(columns=['License Type', 'Name', 'Main Address*', 'Mailing Address', | |
'Name Type', 'License Number', 'Rank', 'Status', 'Expires']) | |
#For loop through 103 pages | |
for page in range(1, 104): | |
#Get search results from url | |
url = "https://www.myfloridalicense.com/wl11.asp?mode=3&search=&SID=&brd=&typ=" | |
data = { | |
"hSearchOpt":"Organization", | |
"hSearchAltName":"Alt", | |
"hDivision":"ALL", | |
#Cosmetologists | |
"hBoard":"05", | |
"hLicenseType":"0501", | |
#Manatee county | |
"hCounty":"51", | |
"hState":"FL", | |
"hCurrPage":"1", | |
"hTotalPages":"103", | |
"hTotalRecords":"5145", | |
"hPageAction":"1", | |
#Max results | |
"hRecsPerPage":"50", | |
#Loop through page number | |
"Page":"{0}".format(page), | |
"SearchGo.x":"0", | |
"SearchGo.y":"0" | |
} | |
response = requests.post(url, data=data) | |
doc = BeautifulSoup(response.content, "html.parser") | |
# Grab all the cosmetologists from table | |
table = doc.find("table", attrs={'bgcolor':'#b6c9dc'}) | |
rows = table.find_all("tr")[1:] | |
# Cosmetologists have five cells, addresses have one | |
for n in range(0,50): | |
# Grab first five cells in row | |
start = n*5 | |
end = start+5 | |
# Grab address cell | |
start_addresses = n | |
try: | |
# Cosmetologist cells span one column, addresses span six | |
cosmetologist = rows[0].find_all("td", attrs={"colspan":"1"})[start:end] | |
addresses = rows[0].find_all("td", attrs={"align":"left", "colspan":"6"}) | |
addresses = [start_addresses] | |
except: | |
print('done') | |
# Get out of the for loop once you reach the end of the list | |
break | |
# Try to get main address | |
try: | |
main = addresses.find_all("td")[1].text.strip() | |
except: | |
main = None | |
# Try to get mailing address | |
try: | |
mailing = addresses.find_all("td")[3].text.strip() | |
except: | |
mailing = None | |
# Try to get rank | |
try: | |
rank = cosmetologist[3].get_text(separator=",").split(',')[1] | |
except: | |
rank = None | |
# Try to get rank | |
try: | |
expires = cosmetologist[4].get_text(separator=",").split(',')[1] | |
except: | |
expires = None | |
# Write dictionary that includes all table contents in one row | |
row = { | |
'License Type': cosmetologist[0].text.strip(), | |
'Name': cosmetologist[1].text.strip(), | |
'Main Address*': main, | |
"Mailing Address": mailing, | |
'Name Type': cosmetologist[2].text.strip(), | |
"License Number": cosmetologist[3].get_text(separator=",").split(',')[0], | |
"Rank": rank, | |
"Status": cosmetologist[4].get_text(separator=",").split(',')[0], | |
"Expires": expires | |
} | |
# Write row to dict | |
df = df.append(row, ignore_index=True) | |
print('Completed page: {0}'.format(page)) | |
# Write df to csv | |
df.to_csv('cosmetologists.csv', index=False) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment