Selenium爬取淘宝商品信息

from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from urllib.parse import quote
from pyquery import PyQuery as pq
import pymongo


browser=webdriver.Chrome()
wait=WebDriverWait(browser,10)
KEYWORD='iPad'

def index_page(page):
    print('正在爬取第{}页'.format(page))
    try:
        url='https://s.taobao.com/search?q='+quote(KEYWORD)
        browser.get(url)
        if page>1:
            input=wait.until(
                EC.presence_of_element_located((By.CSS_SELECTOR,'input.J_Input')))
            submit=browser.find_element_by_css_selector('.inner.clearfix div.form span.btn.J_Submit')
            input.clear()
            input.send_keys(page)
            submit.click()
        wait.until(
            EC.text_to_be_present_in_element((By.CSS_SELECTOR,'.item.active'),
                                             str(page)))
        wait.until(
            EC.presence_of_element_located((By.CSS_SELECTOR,'.item.J_MouserOnverReq  ')))
        get_products()
    except TimeoutException:
        index_page(page)
        
def get_products():
    html=browser.page_source
    doc=pq(html)
    items=doc('.item.J_MouserOnverReq  ').items()
    for item in items:
        product={
            'image':'https:'+item.find('.J_ItemPic.img').attr('data-src'),
            'price':item.find('.price.g_price.g_price-highlight').text(),
            'deal':item.find('.deal-cnt').text(),
            'title':item.find('.row.row-2.title').text(),
            'shop':item.find('.shopname').text(),
            'location':item.find('.location').text(),
        }
        print(product)
        save_to_mongo(product)
        
MONGO_URL='localhost'
MONGO_DB='test'
MONGO_COLLECTION="products"
client=pymongo.MongoClient(MONGO_URL)
db=client[MONGO_DB]

def save_to_mongo(result):
    try:
        if db[MONGO_COLLECTION].insert(result):
            print('成功存储到MongoDB')
    except Exception:
        print('Failed!')
        
MAX_PAGE=100
def main():
    for i in range(MAX_PAGE):
        index_page(i+1)
        
main()