Selenium+Chrome抓取淘宝数据

在学习了网易云课堂上崔庆才老师的Python3爬虫三大案例实战分享之后模仿了一段代码，PhantomJS和MongoDB还没学，暂时没放进去，用pandas代替。

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
import re
from pyquery import PyQuery as pq
import pandas as pd

browser = webdriver.Chrome()
wait = WebDriverWait(browser, 10)
totaldata = []
def search():
    global totaldata
    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('鸡蛋')
        submit.click()
        total = wait.until(
            EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.total"))
        )
        totaldata.extend(get_products())
        return total.text
    except TimeoutException:
        return search()

def next_page(page_number):
    global totaldata
    try:
        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)))
        totaldata.extend(get_products())
    except TimeoutException:
        return next_page(page_number)

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()
    data = []
    for item in items:
        product = {
            'image': item.find('.pic .img').attr('src'),
            'price': item.find('.price').text().replace('\n', ''),
            'deal': item.find('.deal-cnt').text()[:-3],
            'title': item.find('.title').text().replace('\n', ''),
            'shop': item.find('.shop').text(),
            'location': item.find('.location').text()
        }
        data.append(product)
    return data

def main():

    search()
    total = search()
    total = int(re.compile('(\d+)').search(total).group(1))
    for i in range(2, total+1):
        next_page(i)
    df = pd.DataFrame(totaldata)
    df.to_excel('taobaoeggs.xlsx')

if __name__ == '__main__':
    main()