最近项目有些需求，抓取淘宝的搜索商品，抓取的品类还多。直接用selenium+PhantomJS 抓取淘宝搜索商品，快速完成。
#-*- coding:utf-8 -*-
__author__ =‘‘
import logging
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time,re
from tqdm import tqdm
from pyquery import PyQuery as pq
from tianmao.data_tmall import keywords
from dbutils import mysql_util
from config import retry_count
"""
抓取天猫，
"""
logging.basicConfig(level=logging.INFO,
format=‘%(asctime)s [%(levelname)s] [%(filename)s] [%(threadName)s] [line:%(lineno)d] [%(funcName)s] %(message)s‘,
datefmt=‘%Y-%m-%d %H:%M:%S‘)
class tianmao_spider(object):
def __init__(self):
self.SERVICE_ARGS = [‘--disk-cache=true‘,‘--load-images=false‘]
self.target_url =‘https://www.tmall.com/‘
self.browser = webdriver.PhantomJS(service_args=self.SERVICE_ARGS)
self.wait = WebDriverWait(self.browser, 10) #设置10秒超时
self.browser.set_window_size(1400, 900)
# self.browser.add_cookie()
self.mysql_util = mysql_util()
def search(self, category, keyword, page=2):
print(‘正在搜索:{0}‘.format(keyword))
total = 0
for i in range(0, retry_count): #重试3次，3次不成功则跳过
try:
self.browser.get(self.target_url)
input = self.wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, "#mq"))
)
submit = self.wait.until(
EC.element_to_be_clickable((By.CSS_SELECTOR, ‘#mallSearch > form > fieldset > div > button‘)))
input.send_keys(keyword)
submit.click()
total = self.wait.until(
EC.presence_of_all_elements_located((By.CSS_SELECTOR, ‘#content > div > div.ui-page > div > b.ui-page-skip > form‘)))
if page == 2: # 从首页开始抓取
self.get_products(category, keyword)
total = int(re.compile(‘(\d+)‘).search(total[0].text).group(1))
break
except TimeoutException as e:
logging.info("正在重试第{0}次，出现：{1}".format(i + 1, e))
if i == retry_count - 1: # 将类目和搜索关键字按字典写入txt
f = open(‘tmall_retry_crawl.txt‘, ‘a‘, encoding=‘utf-8‘)
f.write(category + ":" + keyword + ‘\n‘)
time.sleep(1)
return total
def get_products(self, category, keyword):
self.wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, ‘#J_ItemList‘)))
html = self.browser.page_source
doc = pq(html)
items = doc(‘#J_ItemList .product‘).items()
for item in items:
#下载图片
img_url = item.find(‘img‘).attr(‘src‘) if item.find(‘img‘).attr(‘src‘) != None else item.find(
‘img‘).attr(‘data-src‘)
if img_url != None:
if not str(img_url).startswith("http"):
img_url = ‘http:{0}‘.format(img_url)
img_save_path = ‘‘ #IMG_PATH + ‘/{0}.jpg‘.format(uuid.uuid4())
#download_img(img_url, img_save_path)
#获取详情页面
item_url = item.find(‘a‘).attr(‘href‘)
logging.info(‘详情页面url：{0}‘.format(item_url))
if item_url == None:
item_detail = ‘‘
else:
if not str(item_url).startswith(‘http‘):
item_url = "https:" + item_url
# item_detail = get_item_detail(item_url)
item_detail = ‘‘
#保存到MySQL
product = {
‘target‘: ‘tmall‘,
‘category‘: category,
‘keyword‘: keyword,
‘item_url‘: item_url,
‘image_url‘: img_url,
‘image_save_path‘: img_save_path, #div:nth-child(3) >
‘title‘: item.find(‘div > div.productTitle‘).text(),
‘price‘: item.find(‘div > p.productPrice‘).text(),
‘deal‘: item.find(‘div > p.productStatus‘).text().replace(‘阿里旺旺‘,‘‘).strip(),
‘shop‘: item.find(‘div > div.productShop‘).text(),
‘location‘: ‘‘,
‘item_detail‘: item_detail,
‘create_time‘: time.strftime(‘%Y-%m-%d %H:%M:%S‘, time.localtime(time.time()))
}
self.mysql_util.sava_to_mysql(‘t_tmall‘, product)
def next_page(self, page_number, category, keyword):
for i in range(0, retry_count): #重试3次
try:
input = self.wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, "#content > div > div.ui-page > div > b.ui-page-skip > form > input.ui-page-skipTo"))
)
submit = self.wait.until(EC.element_to_be_clickable(
(By.CSS_SELECTOR, ‘#content > div > div.ui-page > div > b.ui-page-skip > form > button‘)))
input.clear()
input.send_keys(page_number)
submit.click()
self.wait.until(EC.element_to_be_clickable(
(By.CSS_SELECTOR, ‘#content > div > div.ui-page > div > b.ui-page-skip > form > button‘)))
self.get_products(category, keyword)
break
except TimeoutException as e:
logging.info(e)
time.sleep(0.5)
# self.next_page(page_number, category, keyword)
def start_crawler(self, page=2):
try:
for category in keywords.keys():
keyword_list = keywords[category]
for keyword in keyword_list:
total = self.search(category, keyword, page=page)
# total = int(re.compile(‘(\d+)‘).search(total).group(1))
for i in tqdm(range(page, total + 1)):
print(‘总共{0}页,正在翻第{1}页，抓取类别：{2}，搜索关键字：{3}‘.format(total, i, category, keyword))
self.next_page(i, category, keyword)
if page != 2: # 下一个产品必须从第二页开始抓取，中断后可以直接从中断页继续抓取
page = 2
time.sleep(0.5)
except Exception as e:
print(e)
finally:
self.browser.close()
if __name__ == ‘__main__‘:
tmall = tianmao_spider()
tmall.start_crawler()
