回圈瀏覽頁面時硒卡住了

我撰寫了從站點提取文本并分析它們的可讀性的代碼。但是，我有時會卡在網站上。如果我的程式花費的時間超過 x 秒，有什么方法可以讓我的程式跳到 for 回圈的下一次迭代？如果有任何問題或澄清，請在評論中告訴我

import time
import numpy as np
import pandas as pd
import openpyxl
import reqto as rq
from bs4 import BeautifulSoup
# from SpacySylGetter import *
# import readability
import selenium
from selenium import webdriver

TextIn = pd.read_excel('C:\\Users\\Max von Klemperer\\Desktop\\KeywordLinks\\Aus2.xlsx')

# print(TextIn)
WebURLs = list(TextIn["URL"].values)
Region = list(TextIn["Region"].values)
Keywords = list(TextIn["Keyword"].values)
Rankings = list(TextIn["Ranking"].values)
spaces = 0
syls = 0
counter = 0
characters = 0
sentences = 0
CLIs = []
FL = []
FLAuto = []
WebTexts = []
goodurl = []
goodKW = []
goodRegion = []
goodRanking = []
driver = webdriver.Chrome('C:\\Users\\Max von Klemperer\\Downloads\\chromedriver.exe')

for i in WebURLs:
    try:
        time.sleep(1)
        url = i
        driver.get(url)
        el = driver.find_element_by_tag_name('body')
        initText = el.text

        TextPros = ''.join(
            filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPGQRSTUVWXYZ-.?! \n', initText))
        cleanedStr = ' '.join(TextPros.split())
        print(i)
        textToProc = cleanedStr[600:len(cleanedStr) - 600]
        textToProc.replace("...", ".")
        textToProc.replace("-", " ")
        textToProc.replace(".com", " ")
        if 1000 < len(textToProc) < 100000:
            print(textToProc)
            WebTexts.append(textToProc)
            goodurl.append(i)
            goodRegion.append(Region[counter])
            goodKW.append(Keywords[counter])
            goodRanking.append(Rankings[counter])
        counter = counter   1

    except Exception:
        print("Bounced")

for i in WebTexts:
    words = len(i.split())
    commas = i.count(",")
    spaces = i.count(" ")
    Hyphens = i.count("-")
    # syls = sylsGet(i)
    # print(syls)
    characters = len(i) - spaces - sentences
    sentences = i.count(".")   i.count("?")   i.count("!")
    characters = len(i) - spaces - sentences - commas - Hyphens
    CLI = ((5.89 * (characters / words)) - (0.296 * sentences / (words / 100))) - 15.8
    CLIs.append(CLI)
    print(CLI)
    # FLK = 206.835 - (1.015 * words / sentences) - (84.6 * syls / words)
    # print(FLK)
    # FL.append(FLK)

driver.close()
CLIExcel = pd.DataFrame()

toAdd1 = np.array(goodurl)
toAdd2 = np.array(CLIs)
toAdd3 = np.array(goodRegion)
toAdd4 = np.array(goodKW)
toAdd5 = np.array(goodRanking)
# toAdd6 = np.array(FL)

CLIExcel["URL"] = toAdd1
CLIExcel["CLI's"] = toAdd2
CLIExcel["Region"] = toAdd3
CLIExcel["Keyword"] = toAdd4
CLIExcel["Ranking"] = toAdd5
# CLIExcel["Flesch Kinkaid"] = toAdd6

print(CLIExcel)
CLIExcel.to_excel('C:\\Users\\Max von Klemperer\\Desktop\\WorkedCLI.xlsx')

uj5u.com熱心網友回復：

將您的行替換el = driver.find_element_by_tag_name('body')為

timeout = 10
try:
    el = WebDriverWait(driver, timeout).until(EC.presence_of_element_located((By.TAG_NAME, 'body')))
except TimeoutException:
    continue

這將等待元素出現 10 秒，如果未找到，continue將從 for 回圈中的下一個 url 繼續。

您還需要以下匯入：

from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait

標籤：Python 硒

上一篇：如果它失敗了需要再次運行代碼，還有嗎？

下一篇：如何在沒有屬性錯誤的情況下始終如一地獲取資訊？