Last active
June 24, 2020 16:22
-
-
Save SnowyPainter/00e4c210776536029b8feed4ee856868 to your computer and use it in GitHub Desktop.
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 os | |
import time | |
from selenium import webdriver | |
from collections import defaultdict | |
def getOptions(select): | |
return select.find_elements_by_tag_name("option") | |
def getOptgroups(select): | |
return select.find_elements_by_tag_name("optgroup") | |
def getYears(select): | |
selyears = getOptions(select)[1:] | |
years = [] | |
for y in selyears: | |
years.append(y.text) | |
return years | |
url = 'https://www.edmunds.com/car-reviews/' | |
driver = webdriver.Chrome("/usr/lib/chromium-browser/chromedriver") | |
driver.get(url) | |
time.sleep(2) | |
selmake_element = driver.find_element_by_name("select-make") | |
selmake_element.click() | |
options = getOptions(selmake_element)[1:] | |
allcars = defaultdict(dict) | |
urls = defaultdict(dict) | |
for o in options: | |
brand = o.text | |
cars = {} | |
o.click() | |
time.sleep(0.2) | |
selmodel_element = driver.find_element_by_name("select-model") | |
time.sleep(0.2) | |
optgroups = getOptgroups(selmodel_element) | |
selyear_element = driver.find_element_by_name("select-year") | |
if(len(optgroups) > 0): | |
popular = getOptions(optgroups[0]) | |
others = getOptions(optgroups[1]) | |
for p in popular: | |
p.click() | |
selyear_element.click() | |
cars[o.text] = getYears(selyear_element) | |
for o in others: | |
o.click() | |
selyear_element.click() | |
cars[o.text] = getYears(selyear_element) | |
else: | |
models = getOptions(selmodel_element)[1:] | |
for m in models: | |
m.click() | |
selyear_element.click() | |
cars[o.text] = getYears(selyear_element) | |
allcars[brand] = cars | |
for brand in allcars: | |
urls[brand] = {} | |
for car in allcars[brand]: | |
urls[brand][car] = {} | |
urls[brand][car]["reviews"] = [] | |
for year in allcars[brand][car]: | |
urls[brand][car]["reviews"].append("https://www.edmunds.com/{}/{}/{}/review/".format(brand, car, year)) | |
print(allcars.items()) | |
print(urls.items()) | |
driver.quit() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment