from selenium import webdriver
from selenium.common.exceptions import TimeoutException, StaleElementReferenceException
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from pyquery import
 
 PyQuery as pq
browser=webdriver.Chrome()

def search():
    try:
        browser.get(‘https://www.jd.com/‘)
        input=WebDriverWait(browser,10).until(
            EC.presence_of_element_located((By.CSS_SELECTOR,‘#key‘))
        )
        submit=WebDriverWait(browser,10).until(
            EC.element_to_be_clickable((By.CSS_SELECTOR,
 
‘#search > div > div.form > button > i‘))
        )
        input.send_keys("佩奇")
        submit.click()
        total_pages=WebDriverWait(browser,10).until(
            EC.presence_of_element_located((By.CSS_SELECTOR,‘#J_bottomPage > span.p-skip > em:nth-child(1) > b‘))
        )
        get_product_media()
        pages
 
=int(total_pages.text)
        return pages
    except TimeoutException:
        search()

def search_page(number):
    try:
        input = WebDriverWait(browser, 20).until(
            EC.presence_of_element_located((By.CSS_SELECTOR, ‘#J_bottomPage > span.p-skip > input‘))
        )
        submit = WebDriverWait(browser, 20).until(
            EC.element_to_be_clickable((By.CSS_SELECTOR, ‘#J_bottomPage > span.p-skip > a‘))
        )
        input.clear()
        input.send_keys(number)
        submit.click()
        get_product_media()
        # WebDriverWait(browser, 10).until(
        #     EC.text_to_be_present_in_element((By.CSS_SELECTOR,‘#J_bottomPage > span.p-num > a.curr‘),str(number))
        # )
    except StaleElementReferenceException:
        search_page(number)

def get_product_media():
    # try:
    WebDriverWait(browser, 10).until(
                    EC.presence_of_element_located((By.CSS_SELECTOR,‘#J_goodsList .gl-item .p-img‘))
                )
    html=browser.page_source
    doc=pq(html)
    items=doc(‘#J_goodsList .gl-i-wrap ‘).items()
    for item in items:
        product={
            ‘image‘: item.find(‘.p-img‘).attr(‘src‘),
            # ‘price‘: item.find(‘.p-price‘).text()
            # ‘image‘: item.find(‘.p-img a img‘).attr(‘data-lazy-img‘)
        }
        print(product)
        # print(item)






def main():
    pages=search()
    print(type(pages))
    for i in range(2,pages+1):
        search_page(i)





if __name__ == ‘__main__‘:
    main()

運行的時候如果彈出的chrome不是全屏模式，翻頁會不能運行。。。

另：一直無法解析到正確的src，直到看了https://www.cnblogs.com/airnew/p/10101698.html，發現把html = browser.page_source.replace(‘xmlns‘, ‘another_attr‘)，後就可以正確解析了replace(‘xmlns‘, ‘another_attr‘)這是什麽意思，原作者說要把xmls替換，試了下替換成‘an’也會工作，

chromedriver 全屏 翻頁 錯誤