淘宝美食 spider （含图片下载）

安装相关库即可

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 *
from save_image import *
import pymongo

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

browser = webdriver.PhantomJS(service_args=SERVICE_ARGS)
wait = WebDriverWait(browser, 10) #等待时间

browser.set_window_size(1400, 900)

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'))
        )#输入框显示
        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')))

        """
        # mainsrp-pager > div > div > div > div.total   总页数selector
        """
        get_products()
        return total.text
    except TimeoutException:
        return search()


def next_page(page_number):
    print('正在翻页', page_number)
    try:
        """
        输入页数 点击确认
        #mainsrp-pager > div > div > div > div.form > span.btn.J_Submit  
        确认 selector
        """
        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) #翻页失败 重新进行翻页


def get_products():
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-itemlist .items .item'))) #商品全部加载
    """
    #mainsrp-itemlist
    """
    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('.shop').text(),
            'location': item.find('.location').text()
        }
        print(product)
        save_to_mongo(product)
        if product['image']:
            url = "http:" + product['image']
            download_image(url)


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():
    try:
        total = search()
        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()

import os
from bs4 import BeautifulSoup
import requests
from hashlib import md5
def download_image(url):  #下载图片
    print('正在下载:', url)
    try:
        response = requests.get(url)
        if response.status_code == 200:
            save_image(response.content)
        return None
    except ConnectionError:
        return None


def save_image(content):  #b保存图片\
    os_path = os.getcwd()
    path = os_path + "\\"+ str("image")
    file_path = '{0}/{1}.{2}'.format(path, md5(content).hexdigest(), 'jpg') #路径  文件名  后缀  md5(content).hexdigest()为防止下载重复
    #os.getcwd() 方法用于返回当前工作目录。
    #生成16进制的md5  hashlib.md5.digest() 加密后的结果用二进制表示，如果你要看内容可以使用print  hashlib.md5(str).digest()
    #MD5(content)
    print(file_path)
    if not os.path.exists(file_path):#如果路径不存在  就存储
        with open(file_path, 'wb') as f:  #二进制
            f.write(content)
            f.close()

MONGO_URL = 'localhost'
MONGO_DB = 'taobao'
MONGO_TABLE = 'product'

SERVICE_ARGS = ['--load-images=false', '--disk-cache=true']

KEYWORD = '男鞋'#可根据自身需求更改关键字