python3实现爬取淘宝美食代码分享

环境:

ubuntu16.04
python3.5
python库: selenium, pyquery,pymongo, re

要求:

设置×××面浏览器访问,并将商品列表存入mongoDB数据库.

分析过程暂时略过

代码：

#!/usr/bin/env python# -*- coding:utf-8 -*-"""1.爬取淘宝美食的流程- 搜索关键字: 用selenium打开浏览器,模拟输入关键字,并搜索对应的商品列表.- 分析页码并翻页,模拟翻页,查看到所有页面的商品列表.- 分析并提取商品,利用Pyquery分析源码,解析得到商品列表.- 存储到MONGODB数据库,将商品列表信息存储到mongoDB数据库."""from selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.common.exceptions import TimeoutExceptionfrom pyquery import PyQuery as pqimport refrom anli.mongoconfig import *import pymongoclient = pymongo.MongoClient(MONGO_URL)db = client[MONGO_DB]#设置×××面访问opt = webdriver.FirefoxOptions()opt.set_headless()browser = webdriver.Firefox(options=opt)#等待浏览器加载页面成功.wait = WebDriverWait(browser,10)def search():  try:    # 后台打开浏览器    browser.get('https://www.taobao.com')    # 用CSS选择器复制搜索框    input = wait.until(      EC.presence_of_element_located((By.CSS_SELECTOR, '#q'))    )    # 找到搜索按钮.    submit = wait.until(      # EC.element_to_be_clickable((By.CSS_SELECTOR,'#J_TSearchForm .search-button')))      EC.element_to_be_clickable((By.CSS_SELECTOR,'#J_TSearchForm > div.search-button > button')))    # 输入关键字    input.send_keys('美食')    # 点击搜索按钮.    submit.click()    # 输出总共的页数.    total=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'.total')))    # 调取商品列表的函数.    get_products()    return total.text  except TimeoutException: #超时错误.    return search()# 翻页def next_page(page_number):  try:    #注意在firefox和chrome浏览器复制出来的元素不太一样.    #要传入的页码: 到第几页    input = wait.until(      EC.presence_of_element_located((By.CSS_SELECTOR,'input.input:nth-child(2)'))    )    #复制确定按钮的元素:    submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'span.btn:nth-child(4)')))    #清除页码    input.clear()    #输入当前页码    input.send_keys(page_number)    #点击确定按钮.    submit.click()    #判断当前页码是否是当前数字: 复制高亮页码数.    wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR,'span.num'),str(page_number)))    get_products()  except TimeoutException:    next_page(page_number)#解析jquery源码def get_products():  #商品列表:  wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-itemlist .items .item')))  # 获取网页源码  html = browser.page_source  doc = pq(html)  items = doc('#mainsrp-itemlist .items .item').items()  for item in items:    #定义商品列表详细信息的字典    product = {      'title': item.find('.title').text(),      'price': item.find('.price').text(),      'image': item.find('.pic .img').attr('src'),      'shop': item.find('.shop').text(),      'deal': item.find('.deal-cnt').text()[:-3],      'location': item.find('.location').text()    }    print(product)    #将商品列表信息保存到mongoDB数据库.    save_to_mongo(product)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 main():  total = search()  # 用正则表达式只匹配出数字,并打印数字.  total = int(re.compile('(/d+)').search(total).group(1))  print(total)  for i in range(2,total + 1):    next_page(i)if __name__=='__main__':  main()  #关闭×××面浏览器.  browser.quit()#mongoconfig.py#!/usr/bin/env python# -*- coding:utf-8 -*-MONGO_URL = 'localhost'MONGO_DB = 'taobao'MONGO_TABLE = 'meishi'