首先，對不起，我的英語不好。 實際上，我有一個腳本，它可以用python來搜索網站，找到網頁上的評論。 它是用來搜刮網頁上的所有資訊的，但我只想搜刮最后一個帖子。 如何做到這一點呢？ 此外，我還想找到可能在最后一條資訊中發布的網路鏈接，但要有完整的鏈接。 這可能嗎？
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"/span>
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[1]/button[2]/span"/span>)
)
button.click()
# On recherche les commentaires et on affiche le texte >。
comments = driver.find_elements_by_class_name("commentList-item"/span>)
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
timeestamp = 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('-'/span> * 30)
driver.close()
謝謝你的時間回答！
uj5u.com熱心網友回復：
首先我希望你使用正確的定位器，所以不要使用/html/body/main/div[4]/div[1]/div[1]/div[2]/button[2]/span嘗試使用這個CSS選擇器.btn--mode-primary.overflow--wrap-on。
為了獲得最后的評論，你可以使用這個XPath。(//div[@class='commentList-item'])[last()]
因此，為了獲得最后一條評論的詳細資訊，你的代碼可以修改成這樣：
#!/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"/span>
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"/span>)
author = last_comment.find_element_by_xpath(".//span[包含(@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}"/span>
print("posté par", author)
print(content)
print("Publication:", Timestamp)
print("Lien du commentaire:")。
print(comment_url)
print('-'/span> * 30)
driver.close()
UPD
為了獲得頁面上的最后一個元素，正如你在評論中所描述的那樣，你必須將定位器從
last_comment = driver.find_element_by_xpath("(//div[@class='commentList-item']) [last()]"/span>)
to
last_comment = driver.find_element_by_xpath("（//div[@class='commentList-comment']）[last()]")
所以上面的整個代碼將是：
#!/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"/span>
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[包含(@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}"/span>
print("posté par", author)
print(content)
print("Publication:", Timestamp)
print("Lien du commentaire:")。
print(comment_url)
print('-'/span> * 30)
driver.close()
轉載請註明出處，本文鏈接：https://www.uj5u.com/ruanti/318359.html
標籤：