用selenium+Chrome headless爬取淘宝美食

知识点整理:

• 1、由于淘宝的反爬是比较好的，它的请求也比较兜转，因此直接用requests去请求爬取可能会比较难，因此就可以考虑使用selenium自动化模拟浏览器爬取内容；
• 2、 此处主要是涉及到一些selenium等待加载，输入文本内容，提交文本内容简单操作，再者就是跳转到目标页，分析目标页源码结构
• 3、关于selenium的API文档或参数这篇文章:selenium文档

代码如下：

• 配置文件---config.py

MONGODB_URL='localhost'
MONGO_DB = 'taobao'
MONGO_TABLE='taobao'

#SERVICE_ARGS=['--load-images=false','disk-cache=true']#这个参数原本是打算用PantomJS 无界面爬取的，但由新版selenium已经放弃支持PantomJS，所以这个参数不用了，无界面爬取将改为Chrome headless
KEYWORDS='美食'

• 实现代码 ---spider.py

# -*- coding: utf-8 -*-
# @File    : spider.py
# @Software: PyCharm

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.chrome.options import Options
import re
from pyquery import PyQuery as pq
import pymongo
from config import *

chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')#上面三行代码就是为了将Chrome不弹出界面，实现无界面爬取
browser = webdriver.Chrome(chrome_options=chrome_options)
#browser = webdriver.PhantomJS(service_args=SERVICE_ARGS)
wait = WebDriverWait(browser,10)
client = pymongo.MongoClient(MONGODB_URL)
db = client[MONGO_DB]
browser.set_window_size(1400,900)#由于浏览器无界面，设置一下大小保证加载

def search():
    print('正在搜索....')
    try:
        browser.get('https://www.taobao.com/')
        #等待加载完成执行下面代码
        input = wait.until(
            EC.presence_of_element_located((By.CSS_SELECTOR, "#q"))
        )
        submit = wait.until(
            EC.presence_of_element_located((By.CSS_SELECTOR, "#J_TSearchForm > div.search-button > button"))
        )
        input.send_keys(KEYWORDS)#selenium对输入框输入内容
        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:
        search()

def next_page(page_number):
    print('正在翻页，第%s页' % (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.presence_of_element_located((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)))
        get_product()
    except TimeoutException:
        next_page(page_number)

def get_product():
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-itemlist .items .item')))
    html = browser.page_source #selenium获取当前页面源码
    doc = pq(html) #使用pyquery获取想要的信息
    items = doc('#mainsrp-itemlist .items .item').items()
    for item in items:
        product= {
            'image':item.find('.pic .img').attr('src'),
            'price':item.find('.price').text().replace('\n','',1),
            'deal':item.find('.deal-cnt').text(),
            'title':item.find(('.title')).text().replace('\n','',10),
            'shop':item.find('.shop').text(),
            'location':item.find('.location').text()
        }
        #print(product)
        save_to_mongo(product)

def save_to_mongo(result):
    try:
        if db[MONGO_TABLE].insert(result):
            print("存储MongoDB成功",result)
    except Exception:
        print("存储MongoDB失败",result)

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


if __name__ == '__main__':
    main()