爬取淘宝商品信息

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
import re,json
from pyquery import PyQuery as pq
driver = webdriver.Ie()
wait=WebDriverWait(driver,20,0.2)
url = "http://taobao.com"
def search():
    try:
        driver.get(url)
        # 判断页面是否加载成功
        input=wait.until(EC.presence_of_element_located((By.ID,"q")))
        input.send_keys("美食")
        submit=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#J_TSearchForm > div.search-button > button")))
        submit.click()
        #总的页数
        total=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#mainsrp-pager > div > div > div > div.total")))

        get_products()

        return total.text
    except TimeoutError:
        return search()

def next_page(page_number):
    try:
        input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > input")))  #输入框
        submit = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit"))) #确定
        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)))

        get_products()

    except TimeoutError:
        next_page(page_number)

def get_products():
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#mainsrp-itemlist .items .item")))
    html=driver.page_source
    #进行解析
    doc=pq(html)
    items=doc('#mainsrp-itemlist .items .item').items()
    #字典
    for item in items:
        product={
            'image':item.find('.pic .img').attr('src'),#获取SRC属性
            'price':item.find('.price').text(),#商品价格
            'deal':item.find('.deal-cnt').text()[:-3],#成交量  去掉付款人三个字
            'title':item.find(".title").text(),#商品标题
            'shop':item.find(".shop").text(),#店名
            'location':item.find(".location").text()  #地址

        }
        print(product)
        save_data(product)

def save_data(result):
    with open('淘宝商品信息','a+',encoding="utf-8")as f:
        f.write(json.dumps(result,ensure_ascii=False)+'\n')
        f.close()



def main():
    total=search()
    #只打印数字页数,强制转换为int类型
    total=int(re.compile('(\d+)').search(total).group(1))
    print(total)
    for i in range(2,total+1):
        next_page(i)
    driver.quit()


if __name__ == '__main__':
    main()

 

转载于:https://www.cnblogs.com/yaoliping/p/9630357.html