python爬取淘宝信息

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

chrome_driver = r'F:\SHIyanlou\pachong\venv\Lib\site-packages\selenium\webdriver\chrome\chromedriver.exe'
browser = webdriver.Chrome(executable_path=chrome_driver)
wait = WebDriverWait(browser, 10)


KEYWORD = 'iPad'

def index_page(page):
    print('正在爬取第', page, '页')
    try:
        url = url = 'https://s.taobao.com/search?q=' + quote(KEYWORD)
        print(url)
        browser.get(url)
        if page > 1:
            input = wait.until(
                EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > d'
                                                                 'iv.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)
            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))
        )
        wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-itemlist .items .item')))
        get_products()
    except TimeoutException:
        print('fail')
        index_page(page)


from pyquery import PyQuery as pq

def get_products():
    html = browser.page_source
    doc = pq(html)
    items = doc('#mainsrp-itemlist .items .item').items()
    for item in items:
        product = {
            'image': item.find('.pic .img'),
            'price': item.find('.price').text(),
            'deal': item.find('.deal-cnt').text(),
            'title': item.find('.title').text(),
            'shop': item.find('.shop').text(),
            'location': item.find('.location').text()
        }
        print(product)
        save_to_mongo(product)

import pymongo
MONGO_URL = 'localhost'
MONGO_DB = 'taobao'
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('success')
    except:
        print('failed')

MAX_PAGE = 20
def main():
    for i in range(1, MAX_PAGE + 1):
        index_page(i)

main()

因为反爬虫机制，还未测试。（需要登录和滑动验证码）