使用selenium结合PhantomJS爬取淘宝美食并存储到MongoDB

PhantomJS是一种没有界面的浏览器，便于爬虫

1、PhantomJS下载

2、phantomjs无须安装driver，还有具体的api参考：

http://phantomjs.org/api/command-line.html

 

3、配置config.py

 

MONGO_URL = 'localhost:27017'
MONGO_DB = 'taobao'
MONGO_TABLE = 'iphonex'

SEACH_KEYS='iPhoneX'

SERVICE_ARGS=['--disk-cache=true','--load-images=false'] #开启缓存，不加载图片
EXECUTABLE_PATH=r'C:\test\phantomjs-2.1.1-windows\bin\phantomjs.exe'

 

　　

4、爬取如下spider.py

import re

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
from pyquery import PyQuery as pq
from config import *
import pymongo

client=pymongo.MongoClient(MONGO_URL)
db=client[MONGO_DB]

# browser = webdriver.Chrome()
browser=webdriver.PhantomJS(executable_path=EXECUTABLE_PATH,service_args=SERVICE_ARGS)

wait=WebDriverWait(browser,20)
browser.maximize_window() #窗口最大化避免出问题
def save_to_mongo(result):
    try:
        if db[MONGO_TABLE].insert(result):
            print('存储到MongoDB成功',result)
    except Exception:
        print('存储到MongoDB失败',result)

def search(search_key):
    try:
        browser.get("http://www.taobao.com")
        input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#q")))#直到定位到这个元素
        submit= wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, "#J_TSearchForm > div.search-button > button")))  #等到元素可点击
        input.send_keys(search_key)
        submit.click()
        total_pages=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > div.total')))
        return total_pages.text
    except  TimeoutException:
        return search() #超时重试

def next_page(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()
        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)))#判断元素中的值是否和指定内容一致
        get_product()
        print(page_number)
    except  TimeoutException:
        print('超时')
        return next_page(page_number) #超时重试

def get_product():
    wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR,'#mainsrp-itemlist .items .item')))
    html=browser.page_source
    doc=pq(html)
    items=doc('#mainsrp-itemlist .items .item').items()
    for item in items:
        product={
            'image':item.find('.pic img').attr('src'),
            'price':item.find('.price').text(),
            'deal':item.find('.deal-cnt').text()[:-3],
            'title':item.find('.title').text(),
            'shop':item.find('.location').text()
        }
        save_to_mongo(product)

def main():
    try:
        total=search(search_key=SEACH_KEYS)
        total=int(re.compile('(\d+)').search(total).group(1))
        for i in range(2, total+1):
            next_page(i)
    except Exception:
        print('出错啦')
    finally:
        browser.close()


if __name__=='__main__':
    main()