ChromeDriver的安装（爬虫）

一.chromedriver最新版链接下载：https://edgedl.me.gvt1.com/edgedl/chrome/chrome-for-testing/119.0.6045.105/win64/chromedriver-win64.zip

---

二.将解压后的文件粘贴到anaconda3的Scripts中（找到自己的anacondas3的文件路径）

三.利用清华镜像安装selenium

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

如果安装不成功可能需要更新

pip install --upgrade pip

更新后重新启动jupyter再次利用清华镜像安装selenium

之后就可以在jupyter中打代码

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait

browser = webdriver.Chrome()
try:
    browser.get('https://www.baidu.com')
    input = browser.find_element(By.ID,'kw')
    input.send_keys('Python')
    input.send_keys(Keys.ENTER)
    wait = WebDriverWait(browser,10)
    wait.until(EC.presence_of_element_located((By.ID, 'content_left')))
    print(browser.current_url)
    print(browser.get_cookies())
    print(browser.page_source)
finally:
    browser.close()
    
    
    
    

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

browser = webdriver.Chrome()
wait = WebDriverWait(browser, 100)
KEYWORD = 'iphone'

def index_page(page):
    print('正在爬取第',page, '页')
    try:
        url='https://search.jd.com/Search?keyword=' + quote(KEYWORD)
        browser.get(url)
        if page > 1:
            input = wait.until(
                EC.presence_of_element_located((By.CSS_SELECTOR, '#J_bottomPage > span.p-skip > input')))
            submit = wait.until(
                EC.element_to_be_clickable((By.CSS_SELECTOR, '#J_bottomPage > span.p-skip > a')))
            input.clear()
            input.send_keys(page)
            submit.click()
        wait.until(
            EC.text_to_be_present_in_element((By.CSS_SELECTOR, '#J_bottomPage > span.p-num > a.curr').str(page)))
        wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#J_goodsList > ur')))
        get_products()
    except TimeoutException:
        index_page(page)
from pyquery import PyQuery as pq
def get_products():
    html = browser.page_source
    doc = pq(html)
    items =doc( '#J_goodsList > ur > li').items()
    for item in items:
        product = {
            'image': item.find('.p-img img').attr('src'),
            'price':item.find('.p-price strong').text(),
            'deal':item.find('.p-commit strong').text(),
            'title':item.find('.p-name em').text(),
            'shop':item.find('.J_im_icon a').text()
        }
        print(product)
MAX_PAGE = 30
if __name__ == '__main__':
    for i in range(1,MAX_PAGE + 1):
        index_page(i)