Python使用Selenium爬取淘宝异步加载的数据方法

Python  /  管理员 发布于 7年前   238

淘宝的页面很复杂，如果使用分析ajax或者js的方式，很麻烦

抓取淘宝‘美食'上面的所有食品信息

spider.py

#encoding:utf8import refrom selenium import webdriverfrom selenium.common.exceptions import TimeoutExceptionfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom bs4 import BeautifulSoupfrom config import *import pymongoclient=pymongo.MongoClient(MONGODB_URL)db=client[MONGODB_DB]##这里使用PhantomJS，并配置了一些参数browser=webdriver.PhantomJS(service_args=SERVICE_ArGS)##窗口的大小，不设置的话，默认太小，会有问题browser.set_window_size(1400,900)wait=WebDriverWait(browser, 10)def search():  print('正在搜索')##容易出现超时的错误  try:##等待这两个模块都加载好    browser.get("https://www.taobao.com")    input = wait.until(        EC.presence_of_element_located((By.CSS_SELECTOR, '#q'))      )    submit=wait.until(        EC.element_to_be_clickable((By.CSS_SELECTOR, '#J_TSearchForm > div.search-button > button'))      )    ######这块python2搞得鬼    #input.send_keys('\u7f8e\u98df'.decode("unicode-escape"))    input.send_keys(KEYWORD.decode("unicode-escape"))    submit.click()    total = wait.until(        EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.total'))      )    get_product()    return total.text  except TimeoutException:    return search()def next_page(page_number):  print('翻页'+str(page_number))  try:    input = wait.until(          EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > input'))        )    submit=wait.until(        EC.element_to_be_clickable((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit'))      )    input.clear()    input.send_keys(page_number)    submit.click()##判断是否翻页成功 高亮的是不是输入的值，直接加在后面即可    wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > ul > li.item.active > span'),str(page_number)))    get_product()  except TimeoutException:    return next_page(page_number)#获取产品信息def get_product():  products = wait.until(    EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-itemlist .m-itemlist .items'))        )##拿到网页  html = browser.page_source  soup = BeautifulSoup(html,'lxml')  items = soup.select('#mainsrp-itemlist .m-itemlist .items .item.J_MouserOnverReq')#  print('*************************到此*************')  for item in items:    img = item.select('.J_ItemPic.img')[0].get('src')    price = item.select('.price.g_price.g_price-highlight > strong')[0].get_text()    deal = item.select('.deal-cnt')[0].get_text()    title= item.select('.row.row-2.title > a ')[0].get_text().strip() #:nth-of-type(3)    shop = item.select('.row.row-3.g-clearfix > .shop > a > span:nth-of-type(2)')[0].get_text()     location = item.select('.location')[0].get_text()    product={      'img':img,      'price':price,      'deal':deal,      'title':title,      'shop':shop,      'location':location    }#打印一下    import json    j = json.dumps(product)    dict2 = j.decode("unicode-escape")    print dict2    save_to_mongo(product)def save_to_mongo(product):  try:    if db[MONGODB_TABLE].insert(product):      print('存储到mongodb成功'+str(product))  except Exception:    print("存储到mongodb失败"+str(product))def main():  try:    total=search()    ##搜寻 re正则表达式    s=re.compile('(\d+)')    total=int(s.search(total).group(1))    for i in range(2,total+1):      next_page(i)  except Exception:    print('出错')  finally:    browser.close()if __name__ == '__main__':  main()

config.py

MONGODB_URL='localhost'MONGODB_DB='taobao'MONGODB_TABLE='meishi'SERVICE_ArGS=['--load-images=false','--disk-cache=true']##就是美食这两个字，直接用汉字会报错KEYWORD='\u7f8e\u98df'

以上这篇Python使用Selenium爬取淘宝异步加载的数据方法就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。