selenium抓取淘宝商品信息

利用selenium抓取淘宝商品搜索页的信息。试了一下调用chrome，速度确实不快。后续可以通过使用PhantomJS无界面浏览器来改善。

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import re
from pyquery import PyQuery as pq

browser = webdriver.Chrome()
wait = WebDriverWait(browser,10)
keyword = '美食'

def search():
    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:
        pass

def next_page(page_number):
    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()

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('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)
def main():
    total = search()
    total = re.compile('(\d+)').search(total).group(1)
    for i in range(2,int(total)+1):
        next_page(str(i))

if __name__ == '__main__':
    main()