用selenium爬取淘宝美食

1. spider.py文件如下

  1 __author__ = 'Administrator'
  2 from selenium import webdriver
  3 from selenium.webdriver.common.by import By
  4 from selenium.webdriver.support.ui import WebDriverWait
  5 from selenium.webdriver.support import expected_conditions as EC
  6 import re
  7 from pyquery import PyQuery as pq
  8 from config import *
  9 import pymongo
 10 
 11 client = pymongo.MongoClient(MONGO_URL)
 12 db = client[MONGO_DB]
 13 
 14 browser = webdriver.Chrome()
 15 """
 16 如果把Chrome修改为使用PhantomJS
 17 1. 首先需要安装phantomJS
 18 2. 自定义一些配置参数，这里不加载图片以及使用缓存
 19 browser = webdriver.PhantomJS(service_args=SERVICE_ARGS)
 20 3. 设置窗口大小
 21 browser.set_window_size(1400,900)
 22 """
 23 
 24 wait = WebDriverWait(browser, 10)
 25 
 26 
 27 def search():
 28     # print('正在搜索')  用于phantomJS调试
 29     try:
 30         browser.get('https://www.taobao.com')
 31         input1 = wait.until(
 32             EC.presence_of_element_located((By.CSS_SELECTOR, '#q'))
 33         )
 34         submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '#J_TSearchForm > div.search-button > button')))
 35         # 这里的美食可以替换为配置文件中的变量KEYWORD
 36         input1.send_keys('美食')
 37         submit.click()
 38         total = wait.until(
 39             EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.total')))
 40         # 调用get_products
 41         get_products()
 42         return total.text
 43 
 44     except TimeoutError:
 45         return search()
 46 
 47 
 48 # 使用翻页输入框来翻页
 49 def next_page(page_number):
 50     # print('正在翻页',page_number) 用于phantomJS调试
 51     try:
 52         input1 = wait.until(
 53             EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > input'))
 54         )
 55         submit = wait.until(
 56             EC.element_to_be_clickable((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit'))
 57         )
 58         input1.clear()
 59         input1.send_keys(page_number)
 60         submit.click()
 61         # 根据选择页面会高亮这个条件，来判断是否成功跳转
 62         wait.until(EC.text_to_be_present_in_element(
 63             (By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > ul > li.item.active > span'), str(page_number)))
 64         # 调用get_products()
 65         get_products()
 66 
 67     except TimeoutError:
 68         next_page(page_number)
 69 
 70 
 71 # 解析信息
 72 def get_products():
 73     wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-itemlist .items .item')))
 74     html = browser.page_source
 75     doc = pq(html)
 76     items = doc('#mainsrp-itemlist .items .item').items()
 77     for item in items:
 78         product = {
 79             'image': item.find('.pic .img').attr('src'),
 80             'price': item.find('.price').text(),
 81             'deal': item.find('.deal-cnt').text()[:-3],
 82             'title': item.find('.title').text(),
 83             'shop': item.find('.shop').text(),
 84             'location': item.find('.location').text()
 85         }
 86         print(product)
 87         # 保存数据到mongodb
 88         save_to_mongo(product)
 89 
 90 
 91 # 定义一个保存到mongodb的方法
 92 def save_to_mongo(result):
 93     try:
 94         if db[MON_TABLE].insert(result):
 95             print('存储到MONGODB成功', result)
 96     except Exception:
 97         print('存储到MONGODB失败', result)
 98 
 99 
100 def main():
101     try:
102         # 输出100数字
103         total = search()
104         total = int(re.compile('(\d+)').search(total).group(1))
105         # 调用翻页函数
106         for i in range(2, total + 1):
107             next_page(i)
108     except Exception:
109         print('出错了')
110 
111     finally:
112         browser.close()
113 
114 if __name__ == '__main__':
115     main()

2. config.py

1 __author__ = 'Administrator'
2 MONGO_URL = 'localhost'
3 MONGO_DB = 'taobao'
4 MON_TABLE = 'product'
5 
6 # 配置phantomJS
7 SERVICE_ARGS = ['--load-images=false', '--disk-cache=true']
8 KEYWORD = '美食'