import requests from bs4 import BeautifulSoup import lxml import re import time import random import pymysql.cursors from selenium import webdriver import pandas import numpy connection = pymysql.connect(host='localhost',user='root',password='123',db='aaa',charset='utf8mb4',cursorclass=pymysql.cursors.DictCursor) with connection.cursor() as cursor: sql = "select * from 竞店" cursor.execute(sql) shop_id = cursor.fetchall() connection.commit() payload = { "Ancoding":"gzip, deflate, sdch, br", "Accept-Language":"zh-CN,zh;q=0.8", "Connection":"keep-alive", "Cookie":"hng=; uss=UIMY14A%2B04Bbq%2BqRxS6C9OzJWudsw14Q1kb5mDDqxW%2BQ3YG%2BUcpgrDRWnRQ%3D; uc3=sg2=AC4AfXCJ7XkLw0gCUD1tD9ZxhXFdweN2A6VfybWadxI%3D&nk2=&id2=&lg2=; t=3c0787f77a28e0854ef28fc360b2c555; cookie2=1c912d33e44bdb2008763748702a61f4; _tb_token_=78577371d8136; l=AiQkmjyCyPnG7qTN1Iu5fBqvdCgWvUgn; isg=AvDwL_qYXdDeegACSXGXiIOKwb7f2NSDXgsSOepBvMsepZFPkkmkE0aNixo_; pnm_cku822=; cna=T7gREcWMLDsCAavWmjBJPJpS; Hm_lvt_c478afee593a872fd45cb9a0d7a9da3b=1495496950; Hm_lpvt_c478afee593a872fd45cb9a0d7a9da3b=1495496950", "Host":"tanggulake.tmall.com", "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36", "X-Requested-With":"XMLHttpRequest"} ues_age=["Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1","Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0,""Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50","Opera/9.80 (Windows NT 6.1; U; zh-cn) Presto/2.9.168 Version/11.50","Mozilla/5.0 (Windows; U; Windows NT 6.1; ) AppleWebKit/534.12 (KHTML, like Gecko) Maxthon/3.0 Safari/534.12","Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E)","Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0)","Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E)","Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1 QQBrowser/6.9.11079.201","Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)"] def pig(url): url_re = requests.get(url + "1", params=payload) soup = BeautifulSoup(url_re.text, "lxml") pig = soup.select("div > div > div > div > span:nth-of-type(1)") return (pig[2].text.split("/"))[1] def xingxi(x): ids=[] pigg=[] dates1=[] for pig_id in range(1,int(pig(x))+1): ur1 = x + str(pig_id) url_re1 = requests.get(ur1, params=payload) time.sleep(random.randrange(1,5)) soup = BeautifulSoup(url_re1.text, "lxml") date = soup.select("div > div > div > dl") for spid in date: ids.append(re.sub("\D", "", spid.get("data-id"))) date = soup.select("div > div > div > dl") imgs = soup.select("img") # 图片 for imgasd in imgs: w = imgasd.get("src") p = re.match(r".*//(.*?.jpg)", w) pigg.append(r"https://" + p.group(1)) shuju2 = pandas.DataFrame(pigg) shuju2 = shuju2.rename(columns={0: "图片链接"}) date = soup.select("div > div > div > dl") dated = soup.select("dl") # 获取网页信息 for i in dated: c = list(i.stripped_strings) # 删除空格 b = [elem for elem in c if elem != '￥'] # 过滤 dates1.append([b[0], b[2]]) shuju2 = pandas.DataFrame(pigg) shuju2 = shuju2.rename(columns={0: "图片链接"}) shuju3 = pandas.DataFrame(ids) shuju3 = shuju3.rename(columns={0: "id"}) shuju1 = pandas.DataFrame(dates1) # 写入 shuju1 = shuju1.rename(columns={0: "标题", 1: "价格"}) return pandas.concat([shuju1, shuju2, shuju3], axis=1) def how_much(ids,shop_id): driver = webdriver.PhantomJS() driver.set_window_size(1600, 20000) try: driver.get("http://item.taobao.com/item.htm?id=" + ids) time.sleep(random.randrange(1, 5)) date = driver.page_source except: driver.quit() driver = webdriver.PhantomJS() driver.get("http://item.taobao.com/item.htm?id=" +ids) date = driver.page_source time.sleep(random.randrange(8,13)) soup = BeautifulSoup(date, "lxml") a = [i for i in list(soup.select("script")) if len(str(i)) > 1000] new_time = re.findall(r".*dbst:(.\d*)", str(a[0]).replace(" ", ""))[0][0:10] timeTuple =time.strftime("%Y-%m-%d", time.localtime(int(new_time))) try: color = re.findall(r'<li title="(.*)">颜色分类|li title="(.*)">主要颜色', str(soup.select(".attributes-list"))) color = [i for i in color[0] if i] except: color = "null" try: leimu = soup.select(".tb-pine")[0].get("data-catid") except: leimu = "null" id_dress = "http://item.taobao.com/item.htm?id=" + ids title = "" driver.save_screenshot("C:/Users/高翔/Desktop/乱/"+shop_id+"/" + ids+title.join(re.findall("([\u4e00-\u9fa5])" , driver.title)) + ".jpg") return [color, leimu, id_dress,timeTuple] for dress in shop_id: wite_url=[] with connection.cursor() as cursors: # Create a new sql = 'select id from' + " " + dress["店铺名称"] cursors.execute(sql) fff = cursors.fetchall() fff = [i["id"] for i in fff] connection.commit() result = xingxi(dress["地址"]) for w in result.values: if w[3] not in fff: with connection.cursor() as cursorss: wite_url.append(w[3]) sql = "INSERT INTO " + dress["店铺名称"] + "(`id`,图片链接,价格,标题) VALUES (%s,%s,%s,%s)" cursorss.execute(sql, (w[3], w[2], w[1], w[0])) dates=how_much(w[3],dress["店铺名称"]) sql = "UPDATE " + "花吉" + " SET 颜色='%s',类目='%s',商品地址='%s',上架时间= '%s' where id = '%s'" % (dates[0][0], dates[1], dates[2], dates[3], w[3]) cursorss.execute(sql) connection.commit() with connection.cursor() as cursor: sql = "select * from " + dress["店铺名称"] + " where id in "+str(tuple(wite_url)) print(sql) cursor.execute(sql) shop_id = cursor.fetchall() connection.commit() wite_url.append("1") b = pandas.DataFrame(shop_id).set_index("图片链接").loc[:, ["标题", "商品地址", "价格", "颜色", "类目"]] b.to_csv("C:/Users/高翔/Desktop/乱/"+dress["店铺名称"]+"/"+dress["店铺名称"]+ ".csv")
浙公网安备 33010602011771号