爬取天猫商品信息

1.完整代码

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


def index_page(pages, keyword):
    url = 'https://list.tmall.com/search_product.htm?q=' + quote(keyword)
    brower.get(url)
    for page in range(1, pages + 1):
        print('正在爬取第' + str(page) + '页')
        if page > 1:
            input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.ui-page-skipTo')))
            submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, 'button.ui-btn-s')))
            input.clear()
            input.send_keys(page)
            brower.implicitly_wait(10)
            submit.click()
        wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR, '.ui-page-num'), str(page)))
        get_products(brower)


def get_products(brower):
    html = brower.page_source
    doc = pq(html)
    items = doc('div .product').items()
    for item in items:
        information = []
        image = item.find('div div a img').attr('src')
        information.append(str(image))
        name = item.find('.productTitle a').text()
        information.append(str(name))
        price = item.find('.productPrice em').text()
        information.append(str(price))
        detail = item.find('div div a').attr('href')
        information.append(str(detail))
        shop = item.find('.productShop a').text()
        information.append(str(shop))
        sales = item.find('.productStatus span em').text()
        information.append(str(sales))
        saveinformation(information)
        print(information)




def saveinformation(infors):
    with open('tian_mao.csv', 'w+', newline='', encoding='utf-8') as f:
        writer = csv.writer(f)
        writer.writerow(infors)


if __name__ == '__main__':
    page = int(input("输入页数："))
    keyword = input("输入需要获取的商品名称：")
    brower = webdriver.Chrome()
    wait = WebDriverWait(brower, 20)
    brower.maximize_window()
    index_page(page, keyword)
    brower.quit()

2.爬取第二页时需要手机扫码登录