爬虫练习之Selenium库爬淘宝页面

版权声明：转载请告知 https://blog.csdn.net/weixin_42404145/article/details/81584846

这次练习是跟着崔庆才老师的教程学的..在开始之前确定自己安装了pyquery库和相应的浏览器驱动. 因为有些条件不适用，就改了一些地方，没建项目所以没有存储到数据库中只爬取了数据…在以后的练习中再加入到数据库中吧！
以下是全部代码：

from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from pyquery import PyQuery as pq
import re

browser = webdriver.Firefox()#声明浏览器驱动
wait = WebDriverWait(browser, 10)

def search():
    try:
        browser.get('https://www.taobao.com')#打开页面
        input = wait.until(
                # EC.presence_of_all_elements_located((By.CSS_SELECTOR,'#q'))#在EC.后选择方法要看清自己的选择，之前用all得到的是list会出错
                EC.presence_of_element_located((By.CSS_SELECTOR, '#q'))
    )#找到输入框
        submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#J_TSearchForm > div.search-button > button')))#显式等待，button可点击
        input.send_keys('裙子')
        submit.click()
        total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.total')))
        get_products()#获取第一页的信息
        return total.text
    except TimeoutException:
        return search()


def next_page(page_number):#因为改变页面有很多种方法
    input = wait.until(
        EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > input'))
    )
    submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit')))
    input.clear()
    input.send_keys(page_number)
    submit.click()
    wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > ul > li.item.active > span'),str(page_number)))#高亮区域和要到达的页面一致
    get_products()

def get_products():
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-itemlist .items .item')))
    html = browser.page_source
    doc = pq(html)
    items = doc('#mainsrp-itemlist .items .item').items()#用pyQuery库解析
    for item in items:
        products={
            'price' : item.find('.price').text(),
            'deal' : item.find('.deal-cnt').text()[:-3],
            'title' :item.find('.title').text(),
            'shop' : item.find('.shop').text(),
            'location' : item.find('.location').text()
        }
        print(products)

def main():
    total = search()
    total = int(re.compile('(\d+)').search(total).group(1))
    for i in range(2,total + 1):
        next_page(i)

if __name__ == '__main__':
    main()

结果：