对孔夫子旧书网图书信息进行抓取,并保存为 json、csv、excel 文件格式
最编程
2024-03-12 18:49:21
...
python版本:3.7
需要得引入得包:
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
import re from pyquery import PyQuery as pq
import csv
import xlwt
import json
import codecs
browser = webdriver.Chrome()
wait = WebDriverWait(browser, 10)
all_products = [] #定义一个空列表,用来存储产品信息