Hello!
I'm currently working on making a webscraping script that takes 3 inputs (url, element on page to scrape and the address), but I am stumped on where my script is going wrong.
from selenium import webdriver
import csv
import time
'''Function to scrape data from webpage
The function takes 3 inputs:
1. The url to the website to be scraped
2. Type of element on page to scrape
3. Element name
'''
def ScrapeStore(_link,_searchElementBy,_elementName):
with open('ScrapedAddresses.csv', 'wb') as file: #writes results to file
writer = csv.writer(file, delimiter=',')
driver = webdriver.Firefox() #Launches url in firefox
driver.get(link) #Get link
time.sleep(2) #Pause
#Selects element search method specified in the dictionary
if _searchElementBy == 'c-address':
stores = driver.find_elements_by_class_name(_elementName)
elif _searchElementBy == 'tag_name':
stores = driver.find_elements_by_tag_name(_elementName)
elif _searchElementBy == 'xpath':
stores = driver.find_elements_by_xpath(_elementName)
elif _searchElementBy == 'id':
stores = driver.find_elements_by_id(_elementName)
for store in stores: #for each element on the page
s = store.text #extract text
if s != '': # While not a blank output
# reformat to output each address on one line
s = s.encode('ascii', 'ignore')
s = s.replace('\n',',')
print (s)
writer.writerow([str(s)]) #write to file
file.flush()
driver.quit()
#Function call
ScrapeStore('http://dunkindonutslocationsfinder.com/Dunkin-Donuts-Locations.html/state=NY','class_name','address')
I think something may be wrong with my for loop. The goal is collect addresses and write them to a CSV as the output.
Where do I go from here?
Thanks!
