Selenium+Chrome+PhantomJS爬取淘宝美食

搜索关键字

利用selenium驱动浏览器搜索有关键字，得到查询后的商品列表

分析页码并翻页

得到商品码数，模拟翻页，得到后续页面的商品列表

分析提取商品内容

利用PyQuery分析源码，解析得到商品列表

存储至MongoDB

将商品列表信息存储到数据库MongoDB

 

代码如下：

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,connect=False)
db = client[MONGO_DB]


browser = webdriver.Chrome()
# browser = webdriver.PhantomJS(r'D:phantomjs-2.1.1-windowsinphantomjs.exe')
# browser.set_window_size(1400,900)
wait = WebDriverWait(browser, 10)

def search():
    print('正在搜索')
    try:
        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")))
        input.send_keys(KEYWORD)
        submit.click()
        total = wait.until(
            EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.total"))
        )
        get_products()
        return total.text
    except TimeoutException:
        return search()

def next_page(page_number):
    print('正在翻页',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.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)))
        get_products()
    except TimeoutException:
        next_page(page_number)

def get_products():
    wait.until(EC.presence_of_element_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('data-src'),
            'price':re.sub('\n','',item.find('.g_price').text()),
            'deal':item.find('.deal-cnt').text()[:-3],
            'title':re.sub(r'
',' ',item.find('.title').text()),
            '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_one(result):
            print('存储到MongoDB成功',result)
    except:
        print('存储到MongoDB失败',result)


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


if __name__ == '__main__':
    main()

MONGO_URL = 'localhost'

MONGO_DB = 'toubao'

MONGO_TABLE = 'product'

SERVICE_ARGS = ['--load-images=[false]','--disk-cache=[true]']
# SERVICE_ARGS = [
#     '--proxy=113.106.249.42:80',
#     '--proxy-type=socks5',
# ]

KEYWORD = '美食'

注意

phantomjs已经不再支持selenium模块，所以我这里安装的是旧版本selenium pip install selenium==3.8.0