從字符串中刪除不需要的字符

Question

from selenium import webdriver
import time
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from webdriver_manager.chrome import ChromeDriverManager
from bs4 import BeautifulSoup
import pandas as pd
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
import pandas as pd
from csv import writer


options = webdriver.ChromeOptions()
options.add_argument("--no-sandbox")
options.add_argument("--disable-gpu")
options.add_argument("--window-size=1920x1080")
options.add_argument("--disable-extensions")
driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()))
wait = WebDriverWait(driver, 10)

url = "https://www.askgamblers.com/online-casinos/reviews/casino-friday"
driver.get(url)


soup = BeautifulSoup(driver.page_source, "html.parser")

product = []

pays=soup.select("div#tabPayments")

for pay in pays:
    try:
        t4=pay.select_one(" .review-details-wrapper+ .review-details-wrapper .review-details__item:nth-child(2) .review-details__text")
        t4 = [i for i in t4 if i.text]
    except:
        pass
    
supports = soup.find("div", {"id": "tabCustomers"})
supports = supports.find("div", {"class": "review-details__text"})
email = "Support Email:"+supports.text.replace("\n", "").split(":")[1]
print(email)

他們像這樣給我看 output

['\nSupport\nEmail:\nsupport@casinofriday.com\n', '\n']

但我想要這樣的 output：

 Support Email:support@casinofriday.com 

我想從我的字符串中刪除所有不需要的字符請推薦任何解決方案這些是頁面鏈接https://www.askgamblers.com/online-casinos/reviews/casino-friday

Answer 1

完整代碼

from selenium import webdriver
import time
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from webdriver_manager.chrome import ChromeDriverManager
from bs4 import BeautifulSoup
import pandas as pd
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
import pandas as pd
from csv import writer


options = webdriver.ChromeOptions()
options.add_argument("--no-sandbox")
options.add_argument("--disable-gpu")
options.add_argument("--window-size=1920x1080")
options.add_argument("--disable-extensions")
driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()))
wait = WebDriverWait(driver, 10)

url = "https://www.askgamblers.com/online-casinos/reviews/casino-friday"
driver.get(url)


soup = BeautifulSoup(driver.page_source, "html.parser")

product = []

pays = soup.select("div#tabPayments")

for pay in pays:
    try:
        t4 = pay.select_one(
            " .review-details-wrapper+ .review-details-wrapper .review-details__item:nth-child(2) .review-details__text")
        t4 = [i.replace("\n", "") for i in t4 if i.text]
    except:
        pass
    print(t4)
supports = soup.find("div", {"id": "tabCustomers"})
supports = supports.find("div", {"class": "review-details__text"})
email = "Support Email:"+supports.text.replace("\n", "").split(":")[1]
print(email)

Output

['EWallets:0-1 hours', 'Bank Transfers:1-7 days', 'Cheques:Not offered', 'Card Payments:1-7 days', 'Pending Time:0-24 hours']
Support Email:support@casinofriday.com

希望這可以幫助。 快樂編碼:)

Answer 2

看起來您可以使用兩種方法來實現您的目標：附加之前的 replace() 和 split() 。

Answer 3

您可以使用.replace()方法刪除字符串中不需要的字符，用空字符串替換不需要的字符。
假設您的結果字符串存儲在product字符串中。 因此，要刪除不需要的[符號，您可以這樣做：

product = product.replace('[', '')

對所有要刪除的字符執行此操作將導致如下代碼：

product = product.replace('[', '')
product = product.replace('[', '')
product = product.replace('\n', '')
product = product.replace("'", "")
product = product.replace(",", "")
product = product.strip()

最后的strip()刪除前導和尾隨空格。