爬取京东商城某件商品信息

通过Selenium抓取京东商城某件商品（如“ThinkPad”）的前3页的信息，包括：标题、价格、图片链接、评论数和商品名称，并将这些信息存储至数据库中。

import time
import pymysql
from bs4 import BeautifulSoup
from urllib.parse import quote
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

browser = webdriver.Chrome()
wait = WebDriverWait(browser, 10) #
KEYWORD = 'ThinkPad'

def index_page(page): #抓取商品列表页
    print('正在爬取第', page, '页')
    try:
        url = 'https://search.jd.com/Search?keyword=' + quote(KEYWORD) #
        browser.get(url)
        time.sleep(1)
        browser.execute_script('window.scrollTo(0, document.body.scrollHeight)') #将进度条下拉到最底部
        time.sleep(2)

        wait.until(EC.presence_of_all_elements_located((By.XPATH, '//li[@class="gl-item"]')))
        
        if page > 1:
            input = wait.until(
                EC.presence_of_element_located((By.CSS_SELECTOR, '#J_bottomPage > span.p-skip > input')))
            input.clear()
            input.send_keys(page)
            input.send_keys(Keys.ENTER)
            
            time.sleep(1)
            browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')#将进度条下拉到最底部
            time.sleep(2)
            
            wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR, '#J_bottomPage > span.p-num > a.curr'), str(page)))
            
        get_products()
    except TimeoutException:
#         index_page(page)
        print('index_page: TimeoutException')
    
def get_products():
    html = browser.page_source
    soup = BeautifulSoup(html, 'lxml')
    #标题、价格、图片链接、评论数和商品名称
    for li in soup.select('#J_goodsList li.gl-item'):            
        image = li.select('.p-img > a > img')[0]['data-lazy-img']
        if image == 'done':
            image = li.select('.p-img > a > img')[0].attrs['src'] #注意不要写成atrrs
        product = {
            'image': image,
            'title': li.select('.p-img a')[0].attrs['title'],
            'price': li.select('.p-price > strong')[0].get_text(),
            'commit': li.select('.p-commit > strong > a')[0].get_text(),
            'shop': li.select('.p-shop > span > a')[0].get_text(),
        }
        print(product)
        write_to_sql(product)
        
def create_sql():
    db = pymysql.connect(host='localhost',user='root',password='123456',port=3306)
    cursor = db.cursor()
    cursor.execute("CREATE DATABASE spiders DEFAULT CHARACTER SET utf8") #创建数据库spiders
    db = pymysql.connect(host='localhost', user='root', password='123456', port=3306, db='spiders')
    cursor = db.cursor() 
    sql= "CREATE TABLE JD (image VARCHAR(255) NOT NULL,title VARCHAR(255) NOT NULL,price VARCHAR(255) NOT NULL,commit VARCHAR(255) NOT NULL,shop VARCHAR(255) NOT NULL)"
    cursor.execute(sql) #创建数据表JD
    db.close()
    
def write_to_sql(data):
    table = 'JD'
    keys = ', '.join(data.keys())
    values = ', '.join(['%s'] * len(data))
    sql = 'INSERT INTO {table}({keys}) VALUES ({values}) ON DUPLICATE KEY UPDATE '.format(table=table, keys=keys, values=values)
    update = ','.join(["{key} = %s".format(key=key) for key in data])
    sql += update 
    db = pymysql.connect(host='localhost', user='root', password='123456', port=3306, db='spiders')
    cursor = db.cursor()
    try:
        if cursor.execute(sql, tuple(data.values())*2):
            print('Successful')
            db.commit()
    except:
        print('Failed')
        db.rollback()
    db.close()        
        
def main():
    create_sql()
    for i in range(1, 4):
        index_page(i)
        time.sleep(5)

main()