python --version

pip install selenium

pip install selenium -i https://pypi.tuna.tsinghua.edu.cn/simple

pip install webdriver-manager

# 1. 導(dǎo)入必要的庫(kù)
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
# 2. 自動(dòng)下載并設(shè)置Chrome驅(qū)動(dòng)
service = Service(ChromeDriverManager().install())
# 3. 創(chuàng)建瀏覽器對(duì)象（會(huì)彈出一個(gè)Chrome窗口）
driver = webdriver.Chrome(service=service)
# 4. 打開(kāi)百度首頁(yè)
driver.get("https://www.baidu.com")
# 5. 等待5秒，讓你看到效果
import time
time.sleep(5)
# 6. 關(guān)閉瀏覽器
driver.quit()

# 基礎(chǔ)操作示例代碼
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
import time
# 初始化瀏覽器
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)
try:
    # 訪問(wèn)第一個(gè)網(wǎng)站
    driver.get("https://www.baidu.com")
    print(f"當(dāng)前頁(yè)面標(biāo)題：{driver.title}")
    print(f"當(dāng)前頁(yè)面URL：{driver.current_url}")
    # 等待2秒
    time.sleep(2)
    # 訪問(wèn)第二個(gè)網(wǎng)站
    driver.get("https://www.taobao.com")
    print(f"新頁(yè)面標(biāo)題：{driver.title}")
    # 等待2秒
    time.sleep(2)
    # 后退到百度
    driver.back()
    print(f"后退后頁(yè)面：{driver.title}")
    # 等待2秒
    time.sleep(2)
    # 前進(jìn)到淘寶
    driver.forward()
    print(f"前進(jìn)后頁(yè)面：{driver.title}")
    # 刷新頁(yè)面
    driver.refresh()
    # 最大化窗口
    driver.maximize_window()
    # 設(shè)置窗口大小
    driver.set_window_size(800, 600)
finally:
    # 關(guān)閉瀏覽器
    time.sleep(3)
    driver.quit()
    print("瀏覽器已關(guān)閉")

<input id="kw" name="wd" class="s_ipt" value="" maxlength="255" autocomplete="off">

# HTML元素有id屬性時(shí)使用（id通常是唯一的）
search_input = driver.find_element("id", "kw")
# 或者
search_input = driver.find_element_by_id("kw")

<input id="kw" name="wd" class="s_ipt" value="" maxlength="255" autocomplete="off">

# name屬性可能不唯一，但經(jīng)常使用
search_input = driver.find_element("name", "wd")
# 或者
search_input = driver.find_element_by_name("wd")

<input id="kw" name="wd" class="s_ipt" value="" maxlength="255" autocomplete="off">

# class可能不唯一，一個(gè)元素可能有多個(gè)class
search_input = driver.find_element("class name", "s_ipt")
# 或者
search_input = driver.find_element_by_class_name("s_ipt")

<div>內(nèi)容</div>
<input type="text">
<a href="..." rel="external nofollow" >鏈接</a>

# 通過(guò)標(biāo)簽名查找（最不精確，通常用來(lái)查找多個(gè)元素）
divs = driver.find_elements("tag name", "div")  # 所有div元素
inputs = driver.find_elements("tag name", "input")  # 所有input元素
links = driver.find_elements("tag name", "a")  # 所有鏈接

<a  rel="external nofollow"  rel="external nofollow" >新聞</a>
<a  rel="external nofollow"  rel="external nofollow" >hao123</a>

# 精確匹配鏈接文本
news_link = driver.find_element("link text", "新聞")
hao123_link = driver.find_element("link text", "hao123")

<a  rel="external nofollow"  rel="external nofollow" >百度新聞</a>
<a  rel="external nofollow"  rel="external nofollow" >hao123網(wǎng)址導(dǎo)航</a>

# 部分匹配鏈接文本（包含即可）
baidu_link = driver.find_element("partial link text", "百度")  # 匹配"百度新聞"
hao123_link = driver.find_element("partial link text", "hao123")  # 匹配"hao123網(wǎng)址導(dǎo)航"

# 通過(guò)id
element = driver.find_element("css selector", "#kw")  # #表示id
# 通過(guò)class
element = driver.find_element("css selector", ".s_ipt")  # .表示class
# 通過(guò)標(biāo)簽名+class
element = driver.find_element("css selector", "input.s_ipt")  # input標(biāo)簽且class為s_ipt
# 通過(guò)屬性
element = driver.find_element("css selector", "[name='wd']")  # name屬性為wd
# 組合選擇
element = driver.find_element("css selector", "input#kw.s_ipt[name='wd']")

# 絕對(duì)路徑（從html開(kāi)始）
element = driver.find_element("xpath", "/html/body/div/div[2]/div/div/div/form/span/input")
# 相對(duì)路徑（推薦）
element = driver.find_element("xpath", "http://input")  # 所有input標(biāo)簽
# 帶屬性的相對(duì)路徑
element = driver.find_element("xpath", "http://input[@id='kw']")  # id為kw的input
element = driver.find_element("xpath", "http://input[@name='wd']")  # name為wd的input
# 使用and/or
element = driver.find_element("xpath", "http://input[@id='kw' and @name='wd']")
# 使用文本內(nèi)容
element = driver.find_element("xpath", "http://a[text()='新聞']")  # 文本為"新聞"的鏈接
element = driver.find_element("xpath", "http://a[contains(text(),'新聞')]")  # 包含"新聞"的鏈接

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
# 初始化瀏覽器
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)
try:
    # 打開(kāi)百度
    driver.get("https://www.baidu.com")
    # 各種定位方式的示例
    # 1. 通過(guò)ID定位搜索框
    search_box = driver.find_element(By.ID, "kw")
    # 2. 通過(guò)NAME定位搜索框
    search_box = driver.find_element(By.NAME, "wd")
    # 3. 通過(guò)CLASS_NAME定位搜索框
    search_box = driver.find_element(By.CLASS_NAME, "s_ipt")
    # 4. 通過(guò)TAG_NAME定位所有輸入框
    inputs = driver.find_elements(By.TAG_NAME, "input")
    print(f"找到 {len(inputs)} 個(gè)input元素")
    # 5. 通過(guò)LINK_TEXT定位"新聞"鏈接
    news_link = driver.find_element(By.LINK_TEXT, "新聞")
    # 6. 通過(guò)PARTIAL_LINK_TEXT定位包含"新"的鏈接
    news_links = driver.find_elements(By.PARTIAL_LINK_TEXT, "新")
    print(f"找到 {len(news_links)} 個(gè)包含'新'的鏈接")
    # 7. 通過(guò)CSS_SELECTOR定位
    search_box = driver.find_element(By.CSS_SELECTOR, "#kw")  # id選擇器
    search_box = driver.find_element(By.CSS_SELECTOR, ".s_ipt")  # class選擇器
    search_box = driver.find_element(By.CSS_SELECTOR, "input#kw")  # 標(biāo)簽+id
    # 8. 通過(guò)XPATH定位
    search_box = driver.find_element(By.XPATH, "http://input[@id='kw']")
    search_box = driver.find_element(By.XPATH, "http://*[@id='kw']")
    print("所有定位方式測(cè)試成功！")
finally:
    driver.quit()

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
import time
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)
try:
    driver.get("https://www.baidu.com")
    # 找到搜索框
    search_box = driver.find_element(By.ID, "kw")
    # 方法1：直接輸入
    search_box.send_keys("Python教程")
    time.sleep(2)
    # 方法2：先清空再輸入
    search_box.clear()  # 清空內(nèi)容
    search_box.send_keys("Selenium教程")
    time.sleep(2)
    # 方法3：輸入特殊鍵（如回車(chē)）
    from selenium.webdriver.common.keys import Keys
    search_box.clear()
    search_box.send_keys("自動(dòng)化測(cè)試")
    search_box.send_keys(Keys.ENTER)  # 按回車(chē)鍵
    time.sleep(2)
finally:
    driver.quit()

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
import time
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)
try:
    driver.get("https://www.baidu.com")
    # 找到搜索框并輸入內(nèi)容
    search_box = driver.find_element(By.ID, "kw")
    search_box.send_keys("Python")
    # 方法1：直接點(diǎn)擊百度一下按鈕
    search_button = driver.find_element(By.ID, "su")
    search_button.click()
    time.sleep(2)
    # 方法2：模擬鍵盤(pán)回車(chē)（不需要點(diǎn)擊按鈕）
    driver.back()  # 返回百度首頁(yè)
    time.sleep(1)
    search_box = driver.find_element(By.ID, "kw")
    search_box.clear()
    search_box.send_keys("Selenium")
    search_box.submit()  # 提交表單（相當(dāng)于在輸入框按回車(chē)）
    time.sleep(2)
finally:
    driver.quit()

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)
try:
    driver.get("https://www.baidu.com")
    # 獲取搜索框元素
    search_box = driver.find_element(By.ID, "kw")
    # 獲取元素的各種屬性
    print(f"元素標(biāo)簽名: {search_box.tag_name}")
    print(f"元素ID: {search_box.get_attribute('id')}")
    print(f"元素name: {search_box.get_attribute('name')}")
    print(f"元素class: {search_box.get_attribute('class')}")
    print(f"元素類(lèi)型: {search_box.get_attribute('type')}")
    print(f"元素值: {search_box.get_attribute('value')}")
    print(f"元素是否可見(jiàn): {search_box.is_displayed()}")
    print(f"元素是否可用: {search_box.is_enabled()}")
    print(f"元素是否被選中: {search_box.is_selected()}")
    # 獲取元素位置和大小
    location = search_box.location
    size = search_box.size
    print(f"元素位置: x={location['x']}, y={location['y']}")
    print(f"元素大小: 寬={size['width']}, 高={size['height']}")
    # 獲取元素文本（對(duì)于有文本的元素）
    baidu_link = driver.find_element(By.LINK_TEXT, "百度首頁(yè)")
    print(f"鏈接文本: {baidu_link.text}")
finally:
    driver.quit()

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
from selenium.webdriver.support.select import Select
import time
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)
try:
    # 訪問(wèn)一個(gè)測(cè)試頁(yè)面（包含下拉框）
    driver.get("https://www.w3schools.com/tags/tryit.asp?filename=tryhtml_select")
    # 切換到iframe（因?yàn)檫@個(gè)頁(yè)面有iframe框架）
    driver.switch_to.frame("iframeResult")
    # 找到下拉框
    cars_select = driver.find_element(By.ID, "cars")
    # 創(chuàng)建Select對(duì)象
    select = Select(cars_select)
    # 方法1：通過(guò)可見(jiàn)文本選擇
    select.select_by_visible_text("Audi")
    time.sleep(1)
    # 方法2：通過(guò)value值選擇
    select.select_by_value("opel")
    time.sleep(1)
    # 方法3：通過(guò)索引選擇（從0開(kāi)始）
    select.select_by_index(0)  # 選擇第一個(gè)選項(xiàng)
    time.sleep(1)
    # 獲取所有選項(xiàng)
    all_options = select.options
    print("所有選項(xiàng):")
    for option in all_options:
        print(f"  {option.text} (value: {option.get_attribute('value')})")
    # 獲取已選中的選項(xiàng)
    selected_option = select.first_selected_option
    print(f"當(dāng)前選中: {selected_option.text}")
finally:
    driver.quit()

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
import time
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)
try:
    # 訪問(wèn)測(cè)試頁(yè)面
    driver.get("https://www.w3schools.com/tags/tryit.asp?filename=tryhtml5_input_type_checkbox")
    # 切換到iframe
    driver.switch_to.frame("iframeResult")
    # 找到復(fù)選框
    vehicle1 = driver.find_element(By.ID, "vehicle1")  # 自行車(chē)
    vehicle2 = driver.find_element(By.ID, "vehicle2")  # 汽車(chē)
    vehicle3 = driver.find_element(By.ID, "vehicle3")  # 船
    # 檢查復(fù)選框狀態(tài)
    print(f"自行車(chē)是否選中: {vehicle1.is_selected()}")
    print(f"汽車(chē)是否選中: {vehicle2.is_selected()}")
    print(f"船是否選中: {vehicle3.is_selected()}")
    # 選中復(fù)選框（如果未選中）
    if not vehicle1.is_selected():
        vehicle1.click()
    time.sleep(1)
    if not vehicle2.is_selected():
        vehicle2.click()
    time.sleep(1)
    # 取消選中（如果已選中）
    if vehicle3.is_selected():
        vehicle3.click()
    time.sleep(1)
    # 重新檢查狀態(tài)
    print(f"自行車(chē)是否選中: {vehicle1.is_selected()}")
    print(f"汽車(chē)是否選中: {vehicle2.is_selected()}")
    print(f"船是否選中: {vehicle3.is_selected()}")
finally:
    driver.quit()

import time
time.sleep(5)  # 強(qiáng)制等待5秒，不管元素是否加載完成

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)
# 設(shè)置隱式等待10秒
driver.implicitly_wait(10)
# 之后的所有find_element操作都會(huì)最多等待10秒
driver.get("https://www.baidu.com")
element = driver.find_element("id", "kw")  # 最多等10秒

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)
try:
    driver.get("https://www.baidu.com")
    # 創(chuàng)建等待對(duì)象（最多等10秒，每0.5秒檢查一次）
    wait = WebDriverWait(driver, 10, 0.5)
    # 等待元素出現(xiàn)
    search_box = wait.until(
        EC.presence_of_element_located((By.ID, "kw"))
    )
    print("搜索框已出現(xiàn)")
    # 等待元素可點(diǎn)擊
    search_button = wait.until(
        EC.element_to_be_clickable((By.ID, "su"))
    )
    print("搜索按鈕可點(diǎn)擊")
    # 等待元素可見(jiàn)
    logo = wait.until(
        EC.visibility_of_element_located((By.ID, "lg"))
    )
    print("百度logo可見(jiàn)")
    # 等待文本出現(xiàn)在元素中
    news_link = wait.until(
        EC.text_to_be_present_in_element((By.LINK_TEXT, "新聞"), "新聞")
    )
    print("新聞鏈接文本正確")
finally:
    driver.quit()

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)
try:
    # 1. 設(shè)置隱式等待
    driver.implicitly_wait(5)
    # 2. 訪問(wèn)慢速網(wǎng)站測(cè)試等待
    driver.get("https://the-internet.herokuapp.com/dynamic_loading/2")
    # 3. 點(diǎn)擊開(kāi)始按鈕
    start_button = driver.find_element(By.XPATH, "http://button[text()='Start']")
    start_button.click()
    # 4. 創(chuàng)建顯式等待對(duì)象
    wait = WebDriverWait(driver, 10)
    # 5. 等待加載完成文字出現(xiàn)
    finish_text = wait.until(
        EC.visibility_of_element_located((By.ID, "finish"))
    )
    print(f"加載完成，文字內(nèi)容: {finish_text.text}")
    # 6. 等待特定文本出現(xiàn)
    wait.until(
        EC.text_to_be_present_in_element((By.ID, "finish"), "Hello World!")
    )
    print("成功等到'Hello World!'文本")
finally:
    time.sleep(2)
    driver.quit()

import os          # 文件操作
import time        # 時(shí)間等待
import json        # JSON數(shù)據(jù)處理
import csv         # CSV文件處理
from datetime import datetime  # 時(shí)間處理

class BingImageCrawler:
    def __init__(self, headless=False):
        # 初始化代碼

def search_images(self, keyword, max_images=10):
    # 訪問(wèn)Bing
    # 等待加載
    # 滾動(dòng)加載
    # 解析數(shù)據(jù)

def _scroll_to_load_images(self, max_images):
    # 不斷滾動(dòng)直到加載足夠圖片
    # 處理"加載更多"按鈕

def _parse_images(self, max_count):
    # 獲取每個(gè)圖片元素的JSON數(shù)據(jù)
    # 提取標(biāo)題、描述、URL等信息

def save_data(self, images_data, keyword):
    # 保存為JSON格式
    # 保存為CSV格式（Excel可打開(kāi)）
    # 保存為文本格式

python bing_crawler.py

# 修改搜索關(guān)鍵詞
keyword = "動(dòng)物"  # 改為"汽車(chē)"、"美食"、"星空"等
# 修改圖片數(shù)量
max_images = 20   # 想要獲取的圖片數(shù)量
# 修改是否顯示瀏覽器
headless = True   # True不顯示瀏覽器（后臺(tái)運(yùn)行），F(xiàn)alse顯示瀏覽器

selenium.common.exceptions.NoSuchElementException: Message: no such element

# 1. 增加等待時(shí)間
element = WebDriverWait(driver, 10).until(
    EC.presence_of_element_located((By.ID, "element_id"))
)
# 2. 使用其他定位方式
# 如果id找不到，試試name、class、xpath等
# 3. 檢查是否有iframe
driver.switch_to.frame("iframe_name_or_id")  # 切換到iframe
# 操作元素...
driver.switch_to.default_content()  # 切換回主頁(yè)面

ElementNotInteractableException: element not interactable

# 1. 等待元素可點(diǎn)擊
element = WebDriverWait(driver, 10).until(
    EC.element_to_be_clickable((By.ID, "element_id"))
)
# 2. 使用JavaScript點(diǎn)擊
driver.execute_script("arguments[0].click();", element)
# 3. 滾動(dòng)到元素位置
driver.execute_script("arguments[0].scrollIntoView();", element)
element.click()

TimeoutException: Message: timeout waiting for element

# 1. 增加等待時(shí)間
wait = WebDriverWait(driver, 20)  # 從10秒增加到20秒
# 2. 設(shè)置更頻繁的檢查
wait = WebDriverWait(driver, 10, 0.1)  # 每0.1秒檢查一次
# 3. 檢查網(wǎng)絡(luò)或網(wǎng)站狀態(tài)

WebDriverException: Message: 'chromedriver' executable needs to be in PATH

# 正確的方式
from webdriver_manager.chrome import ChromeDriverManager
service = Service(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)