Skip to content
Advertisement

Web scraping: help needed last post and find link

First, sorry for my poor English.
Actually, I have a script which scrapes a website to find comments in webpage, in python.
Its for scrape all messages in page, but I will want scrape just last post. How to do this please?
Too, I will want to find web links probably posted in last message, but a full link.
Its possible?
Here is the webpage link and script:

https://www.dealabs.com/discussions/suivi-erreurs-de-prix-1063390?page=9999

#!/usr/bin/env python3
# https://www.jeuxvideo.com/forums/42-47-66784467-1-0-1-0-aide-scraping-python-forum-dealabs.htm
# scraping_dealabs.py

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By 

url = "https://www.dealabs.com/discussions/suivi-erreurs-de-prix-1063390?page=9999"

options = Options()
options.headless = True

driver = webdriver.Chrome(options=options)
driver.get(url)

# Accepter les cookies
button = WebDriverWait(driver, 2).until(
    EC.element_to_be_clickable((By.XPATH, "/html/body/main/div[4]/div[1]/div/div[1]/div[2]/button[2]/span"))
)
button.click()

# On recherche les commentaires et on affiche le texte
comments = driver.find_elements_by_class_name("commentList-item")

for comment in comments:
    _id = comment.get_attribute("id")
    author = comment.find_element_by_class_name('userInfo-username').text
    content = comment.find_element_by_class_name('userHtml-content').text
    timestamp = comment.find_element_by_class_name('text--color-greyShade').text
    comment_url = f"{url}#{_id}"

    print("Posté par", author)
    print(content)
    print("Publication:", timestamp)
    print("Lien du commentaire:")
    print(comment_url)
    print('-' * 30)

driver.close()

Thanks for time ans reply!

Advertisement

Answer

First I’d like you to use correct locators, so instead of /html/body/main/div[4]/div[1]/div/div[1]/div[2]/button[2]/span try using this CSS selector .btn--mode-primary.overflow--wrap-on.
In order to get the last comment you can use this XPath: (//div[@class='commentList-item'])[last()] So in order to get the last comment details only your code can be modified to be like this:

#!/usr/bin/env python3
# https://www.jeuxvideo.com/forums/42-47-66784467-1-0-1-0-aide-scraping-python-forum-dealabs.htm
# scraping_dealabs.py

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By 
from selenium.webdriver.common.action_chains import ActionChains

url = "https://www.dealabs.com/discussions/suivi-erreurs-de-prix-1063390?page=9999"

options = Options()
options.headless = True

driver = webdriver.Chrome(options=options)
driver.get(url)

actions = ActionChains(driver)

# Accepter les cookies
WebDriverWait(driver, 2).until(
EC.element_to_be_clickable((By.CSS_SELECTOR, ".btn--mode-primary.overflow--wrap-on"))).click()

last_comment = driver.find_element_by_xpath("(//div[@class='commentList-item'])[last()]")

actions.move_to_element(last_comment).perform()
time.sleep(0.5)
last_comment = driver.find_element_by_xpath("(//div[@class='commentList-item'])[last()]")

_id = last_comment.get_attribute("id")
author = last_comment.find_element_by_xpath(".//span[contains(@class,'userInfo-username')]").text
content = last_comment.find_element_by_xpath(".//*[contains(@class,'userHtml-content')]").text
timestamp = last_comment.find_element_by_xpath(".//*[contains(@class,'text--color-greyShade')]").text
comment_url = f"{url}#{_id}"

print("Posté par", author)
print(content)
print("Publication:", timestamp)
print("Lien du commentaire:")
print(comment_url)
print('-' * 30)

driver.close()

UPD
To get the last element on the page, as you described in the comments, you have to change the locator from

last_comment = driver.find_element_by_xpath("(//div[@class='commentList-item'])[last()]")

to

last_comment = driver.find_element_by_xpath("(//div[@class='commentList-comment'])[last()]")

So that entire code above will be:

#!/usr/bin/env python3
# https://www.jeuxvideo.com/forums/42-47-66784467-1-0-1-0-aide-scraping-python-forum-dealabs.htm
# scraping_dealabs.py

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By 
from selenium.webdriver.common.action_chains import ActionChains

url = "https://www.dealabs.com/discussions/suivi-erreurs-de-prix-1063390?page=9999"

options = Options()
options.headless = True

driver = webdriver.Chrome(options=options)
driver.get(url)

actions = ActionChains(driver)

# Accepter les cookies
WebDriverWait(driver, 2).until(
EC.element_to_be_clickable((By.CSS_SELECTOR, ".btn--mode-primary.overflow--wrap-on"))).click()

last_comment = driver.find_element_by_xpath("(//div[@class='commentList-comment'])[last()]")

actions.move_to_element(last_comment).perform()
time.sleep(0.5)
last_comment = driver.find_element_by_xpath("(//div[@class='commentList-comment'])[last()]")

_id = last_comment.get_attribute("id")
author = last_comment.find_element_by_xpath(".//span[contains(@class,'userInfo-username')]").text
content = last_comment.find_element_by_xpath(".//*[contains(@class,'userHtml-content')]").text
timestamp = last_comment.find_element_by_xpath(".//*[contains(@class,'text--color-greyShade')]").text
comment_url = f"{url}#{_id}"

print("Posté par", author)
print(content)
print("Publication:", timestamp)
print("Lien du commentaire:")
print(comment_url)
print('-' * 30)

driver.close()
User contributions licensed under: CC BY-SA
5 People found this is helpful
Advertisement