一嘿期，結(jié)果

image.png

2.思路

3.上源碼

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


class Amazon(object):

    def __inig__(self):
        pass
        #self.amazon_url = 'https://www.amazon.cn/mn/searchApp?keywords=書(shū)包&searchType=utf8'

    #################數(shù)據(jù)庫(kù)#######
    def mysql(self):
        pass
        # conn = pymysql.Connect(host='x',user='x',password='x',database='a',port=x,charset='x')
        # cursor=conn.cursor()
        # dataname =input('請(qǐng)輸入數(shù)據(jù)庫(kù)名:')
        # sql = 'CREATE TABLE IF NOT EXISTS %s(ID INT(10) NOT NULL PRIMARY KEY AUTO_INCREMENT,' \
        #       'A TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,' \
        #       'COMMODITY VARCHAR(255))ENGINE = INNODB DEFAULT CHARSET=utf8'
        # cursor.execute(sql%dataname)
        # print('創(chuàng)建成功Ｓ直！')

        #keyword字段修改搜索
    def get_amazon_bag(self):
        browser = webdriver.Firefox()
        browser.set_window_size(900,900)
        timeout = WebDriverWait(browser,10)

        time.sleep(3)
        url = 'https://www.amazon.cn/mn/searchApp?keywords=書(shū)包&searchType=utf8'
        browser.get(url)

        timeout.until(EC.presence_of_element_located((By.ID,'atfResults')))

        a = 0
        try:
            while True:
                for down in range(0,10000,1000):
                    browser.execute_script('window,scrollBy(0,{})'.format(down))
                    time.sleep(2)

                    print(a)
                    #if a ==6:
                        #print(browser.page_source)
                    html = browser.page_source
                    soup = BeautifulSoup(html,'lxml')
                    items = soup.find('ul',attrs={'id':'s-results-list-atf'})
                    #解析單個(gè)商品
                    itema = [itema.get_text() for itema in items.find_all('div',class_='s-item-container')]
                    for item in itema:
                        name_a = item.strip().replace('\n\n','')[:100]  #提取前100個(gè)字斩熊，可以修改
                        a +=1
                        print('{}\n{}'.format(a,name_a))

                        #########數(shù)據(jù)庫(kù)#######
                    #     sql = 'INSERT INTO %s(COMMODITY)VALUES("%s")'
                    #     value=(dataname,name_a)
                    #     cursor.execute(sql%value)
                    #
                    # conn.commit()
                    # print('提交成功')
                    #
                    #     #item為當(dāng)個(gè)信息商品信息
                    time.sleep(5)
                    #點(diǎn)擊下一頁(yè)
                    timeout.until(EC.presence_of_element_located((By.ID,'pagnNextString'))).click()
                    time.sleep(4)
                    ####測(cè)試####
                    # cursor.close()
                    # conn.close()
                    # print('測(cè)試關(guān)閉數(shù)據(jù)庫(kù)/游標(biāo)了')
        except Exception as e:
            print(e)
        finally:
            pass
            #關(guān)閉瀏覽器
            # cursor.close()
            # conn.close()
            # print('關(guān)閉數(shù)據(jù)庫(kù)/游標(biāo)里逆！')
            # print('關(guān)閉瀏覽器进胯！')
            # browser.quit()
a = Amazon()
a.get_amazon_bag()