from selenium import webdriver
from scrapy.selector import Selector
import time
import random
import pymysql
from urllib import parse
import re
import os
# a = Selector(text=webdriver.page_source)
# if a.xpath(‘//*[@id="J_submit"]‘):
# time.sleep(15)
# for i in Selector(text=webdriver.page_source).xpath(‘//*[@id="J_ShopSearchResult"]/div/div[2]/div/dl‘):
# bd_pig = i.xpath("./dt/a/img/@src").re(‘.*(img.*?jpg)‘)
# bd_name = i.xpath(‘./dd[1]/a/text()‘).extract_first(‘‘)
# bd_id = i.xpath(‘./dd[1]/a/@href‘).extract_first(‘‘)
# bd_much = i.xpath(‘./dd[1]/div/div[1]/span[2]/text()‘).extract_first(‘‘)
# bd_liang = i.xpath(‘./dd[1]/div/div[last()]/span/text()‘).extract_first(‘‘)
#
# sql = "INSERT INTO " + i.split(",")[0] + "( `id`,图片链接,价格,标题,销量) VALUES (%s,%s,%s,%s,%s)"
# cursor.execute(sql,
# (bd_id, bd_pig, bd_much, bd_name, bd_liang))
# self.connection.commit()
# else:
# for i in Selector(text=webdriver.page_source).xpath(‘//*[@id="J_ShopSearchResult"]/div/div[2]/div/dl‘):
# bd_pig = i.xpath("./dt/a/img/@src").re(‘.*(img.*?jpg)‘)
# bd_name =‘‘.join(re.findall(‘[\u4e00-\u9fa5]‘, i.xpath(‘./dd[1]/a/text()‘).extract_first(‘‘)))
# bd_id = ‘‘.join(re.findall(‘\d‘, i.xpath(‘./dd[1]/a/@href‘).extract_first(‘‘)))
# bd_much = i.xpath(‘./dd[1]/div/div[1]/span[2]/text()‘).extract_first(‘‘)
# bd_liang = i.xpath(‘./dd[1]/div/div[last()]/span/text()‘).extract_first(‘‘)
#
# sql = "INSERT INTO " + shop.split(",")[0] + "( `id`,图片链接,价格,标题,销量) VALUES (%s,%s,%s,%s,%s)"
# cursor.execute(sql,
# (bd_id, bd_pig, bd_much, bd_name, bd_liang))
# conection.commit()
class spider(object):
def chul3(self,dates):
a = Selector(text=dates)
next_url = a.xpath(‘//*[@id="J_ShopSearchResult"]/div/div[2]/div[10]/a[11]/@href‘).extract_first("")
return ‘https:‘+next_url
chuli=spider()
conection = pymysql.connect(host=‘localhost‘,user=‘root‘,password=‘123‘,db=‘7.24测试‘,charset=‘utf8mb4‘,cursorclass=pymysql.cursors.DictCursor)
with conection.cursor() as cursor:
sql1 = "select * from 商品id"
cursor.execute(sql1)
shop_id = cursor.fetchall()
shop_oldid=[i[‘id‘] for i in shop_id]
sql1 = ‘‘‘
SELECT
`商品id`.id,
`上架时间`,‘1天销量‘ as 日期
FROM
`商品id` WHERE TIMESTAMPDIFF(DAY,`上架时间`,CURDATE()) =1 union SELECT
`商品id`.id,
`上架时间`,‘7天销量‘ as 日期
FROM
`商品id` WHERE TIMESTAMPDIFF(DAY,`上架时间`,CURDATE()) =7
union SELECT
`商品id`.id,
`上架时间`,‘30天销量‘ as 日期
FROM
`商品id` WHERE TIMESTAMPDIFF(DAY,`上架时间`,CURDATE()) =30‘‘‘
cursor.execute(sql1)
shop_id = cursor.fetchall()
shop_olxx = [i for i in shop_id]
conection.commit()
cursor =conection.cursor()
webdriver = webdriver.Ie()
url = ‘https://login.taobao.com/member/login.jhtml?spm=a21bo.50862.754894437.1.5dcec6f76Oq9Wh&f=top&redirectURL=https%3A%2F%2Fwww.taobao.com%2F%3Fspm%3Da1z10.1-c-s.1581860521.1.559a715a3EnsHq‘
webdriver.get(url)
time.sleep(20)
def lll(url):
webdriver.implicitly_wait(50)
webdriver.get(url)
myDynamicElement = webdriver.find_element_by_class_name(‘pagination‘)
a=webdriver.page_source
time.sleep(random.randrange(2,6))
selects=Selector(text=a)
for i in selects.xpath(‘//*[@id="J_ShopSearchResult"]/div/div[2]/div/dl‘):
bd_pig = i.xpath("./dt/a/img/@src").re(‘(.*)_‘)
bd_name = ‘‘.join(re.findall(‘[\u4e00-\u9fa5]‘, i.xpath(‘./dd[1]/a/text()‘).extract_first(‘‘)))
bd_id = ‘‘.join(re.findall(‘\d‘, i.xpath(‘./dd[1]/a/@href‘).extract_first(‘‘)))
bd_much = i.xpath(‘./dd[1]/div/div[1]/span[2]/text()‘).extract_first(‘‘)
bd_idlian=‘http://item.taobao.com/item.htm?id=‘+bd_id
bd_liang = i.xpath(‘./dd[1]/div/div[last()]/span[last()]/text()‘).extract_first(‘‘)
if bd_id not in shop_oldid:
sql = "INSERT INTO 商品id (`品牌`, `id`,图片链接,价格,标题,商品地址) VALUES (%s,%s,%s,%s,%s,%s)"
cursor.execute(sql,
(shop.split(",")[0], bd_id, bd_pig, bd_much, bd_name,bd_idlian))
conection.commit()
webdriver.implicitly_wait(50)
webdriver.get(‘http://item.taobao.com/item.htm?id=‘+bd_id)
myDynamicElement = webdriver.find_element_by_class_name(‘tb-price-spec‘)
time.sleep(random.randrange(2, 6))
date=webdriver.page_source
select_xixi = Selector(text=date)
liem = select_xixi.xpath(‘//*[@id="J_TMySize"]/@data-value‘).extract_first("")
sql = ‘update `商品id` set `商品id`.`类目` = %s where id = %s‘
cursor.execute(sql,
(liem, bd_id))
conection.commit()
c=1
ee=1
for i in select_xixi.xpath(‘//*[@id="J_isku"]/div/dl‘):
b = i.xpath(‘./dt/text()‘).extract_first("")
if ‘尺码‘ in b:
aa = i.xpath(‘./dd/ul/li/a/span/text()‘).extract()
ee = len(aa)
dd = ‘ ‘.join(aa)
sql = ‘update `商品id` set `商品id`.`尺码` = %s where id = %s‘
cursor.execute(sql,
(dd, bd_id))
conection.commit()
if ‘颜色‘ in b:
a = i.xpath(‘./dd/ul/li/a/span/text()‘).extract()
c = len(a)
d = ‘ ‘.join(a)
sql = ‘update `商品id` set `商品id`.`颜色` = %s where id = %s‘
cursor.execute(sql,
(d, bd_id))
conection.commit()
w = c * ee
sql= ‘update `商品id` set `商品id`.`sku量` = %s where id = %s‘
cursor.execute(sql,
(w,bd_id))
conection.commit()
title = path + r‘\\‘ +shop.split(",")[0] + r‘\\‘ + ‘‘.join(
re.findall(‘\d‘, i.xpath(‘./dd[1]/a/@href‘).extract_first(‘‘))) + re.sub("\W", "", webdriver.title)
capture(webdriver, title + ‘.jpg‘)
for i in shop_olxx:
if i[‘id‘] == bd_id:
sql = "UPDATE 商品id set " + i[‘日期‘] + " = (%s) where id = %s"
cursor.execute(sql,
(bd_liang, i[‘id‘]))
conection.commit()
if selects.xpath(‘//*[@id="J_ShopSearchResult"]/div/div[2]/div[last()]/a[last()]/@href‘).extract_first(""):
lll(‘https:‘+selects.xpath(‘//*[@id="J_ShopSearchResult"]/div/div[2]/div[last()]/a[last()]/@href‘).extract_first(""))
path=os.getcwd()
def capture(webder, save_fn="capture.png"):
# browser = webdriver.Ie() # Get local session of firefox
# browser.get(url) # Load page
webder.execute_script("""
(function () {
var y = 0;
var step = 100;
window.scroll(0, 0);
function f() {
if (y < document.body.scrollHeight) {
y += step;
window.scroll(0, y);
setTimeout(f, 50);
} else {
window.scroll(0, 0);
document.title += "scroll-done";
}
}
setTimeout(f, 1000);
})();
""")
for i in range(30):
if "scroll-done" in webder.title:
break
time.sleep(1)
webder.save_screenshot(save_fn)
with open(os.getcwd() + r‘\1.csv‘, ‘r‘) as c:
for shop in c.readlines():
url = shop.split(",")[2]
lll(url)
时间： 2024-07-29 19:57:25