selenium学习笔记

使用selenium可以打开百度的网页但是打不开淘宝的网页了

 

# 淘宝使用selenium无法打开了
from selenium import webdriver
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
from urllib.parse import quote
from pyquery import PyQuery

KEYWORD = 'iphonex'
# url='https://s.taobao.com/search?q='
browser = webdriver.Chrome(r'G:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe')
# browser.get("https://www.baidu.com")
wait = WebDriverWait(browser, 10)


def crawl_page(page):
    try:
        url = 'https://s.taobao.com/search?q=' + quote(KEYWORD)
        browser.get(url)

        # 翻页
        if page > 1:
            page_box = wait.until(
                EC.presence_of_element_located(
                    (By.CSS_SELECTOR, '.input.J_Input')
                )
            )
            jump_button = wait.until(
                EC.element_to_be_clickable(
                    (By.CSS_SELECTOR, '.btn.J_Submit')
                )
            )
            page_box.clear()
            page_box.send_keys(page)
            jump_button.click()

        # div.item.J_MouserOnverReq
        # 下面一句意思是通过wait设置的20秒，在这20秒内执行括号里面的内容，如果超时还没有找到就继续向下执行
        wait.until(
            EC.presence_of_element_located(
                (By.CSS_SELECTOR, 'div .item .J_MouserOnverReq')
            )
        )

        get_product()
    except:

        crawl_page(page)


def get_product():
    html = browser.page_source
    doc = PyQuery(html)
    items = doc('div .item.J_MouserOnverReq').items()
    for item in items:
        product = {
            'img': item.find('.img').attr('data-src'),
            'price': item.find('.price').text(),
            'deal': item.find('.deal-cnt').text(),
            'title': item.find('.title').text(),
            'shop': item.find('.shop').text(),
            'location': item.find('.location').text()
        }