day18hw

最新推荐文章于 2024-08-22 22:01:15 发布

weixin_54146878

最新推荐文章于 2024-08-22 22:01:15 发布

阅读量159

点赞数

文章标签： python 开发语言

本文链接：https://blog.csdn.net/weixin_54146878/article/details/127414713

版权

import re
import csv
from bs4 import BeautifulSoup
from selenium.webdriver import Chrome
import requests

def page_open(str1):
    b = Chrome()
    b.get(str1)
    tag = b.find_element_by_id('key')
    tag.send_keys('勋章\n')
    b.switch_to.window(b.window_handles[-1])
    for x in range(100):
        b.execute_script('window.scrollBy(0,1000)')
    return b

def page_over(b):
    over = b.find_element_by_class_name('.pn-next')
    over.click()
    b.switch_to.window(b.window_handles[-1])
    return b



def data(b):

    h1 = b.page_source
    soup = BeautifulSoup(h1, 'lxml')
    div1 = soup.select('#J_goodsList')
    all_data = []
    for x in div1[1:len(div1):1]:
        names = x.select('.p-name p-name-type-2>a').attrs['title']
        prices = x.select('.p-price>strong i').text
        comment = x.select('.p-commit a').text
        shops = x.select('.p-shop>.J_im_icon>.curr-shop hd-shopname').text
        if x.select('.p-icons>i').text != None:
            icons = x.select('.p-icons>i').text
        else:
            icons = ''
        all_data.append([names,prices,comment,shops,icons])
    writer.writerows(all_data)


writer = csv.writer(open('files/勋章.csv', 'wt', encoding='utf-8', newline=''))
writer.writerow(['名称', '价格', '评论数', '店铺名', '标示'])
str1='https://www.jd.com/'
b=page_open(str1)
for x in range(99):
    data(b)
    page_over(b)
data(b)