u010719791的专栏

物流领域应用

python处理机制

51job获取完整代码：import requestsfrom bs4 import BeautifulSoupimport datetimeimport jsonimport xlwings as xwfrom selenium import webdriverimport timeimport pandas as pdfrom selenium.webdriver import Chrome, ChromeOptions, ActionChainsfrom selenium.w.

51job爬取完整代码：import requestsfrom bs4 import BeautifulSoupimport datetimeimport jsonimport xlwings as xwfrom selenium import webdriverimport timeimport pandas as pdfrom selenium.webdriver import Chrome, ChromeOptions, ActionChainsfrom selenium.we

基金收益排名import xlwings as xwimport requestsfrom bs4 import BeautifulSoupfrom datetime import datetimeimport jsonimport xlwtimport xlwings as xwfrom selenium import webdriverimport timeimport pandas as pdimport csvimport refrom selenium.webdriv

Chromedrive下载版本可参照Selenium Chrome版本与chromedriver兼容版本对照表下载地址各版本下载地址geckodriver下载地址淘宝npm镜像geckodriver Mirroriedriver下载地址http://selenium-release.storage.googleapis.com/index.htmlphantomjs驱动下载地址Download PhantomJSoperadriver下载地址淘宝npm镜像Op

百度地图测距：import requestsfrom bs4 import BeautifulSoupfrom datetime import datetimeimport jsonimport xlwtimport xlwings as xwfrom selenium import webdriverimport timefrom selenium.webdriver import Chrome, ChromeOptionsimport pandas as pdimport js

import pandas as pdimport osimport xlwt#文件路径file_dir = r'C:\Users\HONORS\Desktop\进出库'#构建新的表格名称new_filename = file_dir + '\\new_file.xls'#找到文件路径下的所有表格名称，返回列表file_list = os.listdir(file_dir)new_list = []for file in file_list: #重构文件路径 fi.

导入第三方库失败和解调器配置根据字面意思理解，一直以为是pip版本不对导致的，于是花费时间在更新pip版本上。根据导入模块时错误提示信息可以看出，我的pycharm路径为C:\Users\Administrator.USER-20190620KX\PycharmProjects\untitled20\Scripts。在该径路下打开命令窗口，输入python.exe -m pip install matplotlib -i http://pypi.douban.com/simple --trusted-

import pyechartsfrom pyecharts.charts import Barfrom pyecharts.charts import Piefrom pyecharts.charts import Linefrom pyecharts import options as optsbar=Bar()bar.add_xaxis(["衬衫","毛衣","裙子","T学",])bar.add_yaxis("A销售",[120,110,30,40,])bar.add_yaxis(.

完整代码：import xlwings as xwimport requestsfrom bs4 import BeautifulSoupfrom datetime import datetimeimport jsonimport xlwtimport xlwings as xwfrom selenium import webdriverimport timeimport pandas as pdimport csvimport refrom selenium.webdrive

完整代码：import xlwings as xwimport requestsfrom bs4 import BeautifulSoupfrom datetime import datetimeimport jsonimport xlwtimport xlwings as xwfrom selenium import webdriverimport timeimport pandas as pdimport csvimport refrom selenium.webdrive

完整代码：import requestsimport re# 自定义下载页面函数def load_page(url): response = requests.get(url) data = response.content return data# 自定义保存页面图片函数def get_image(html): regx = r'http://[\S]*jpg' # 定义图片正则表达式 pattern = re.compile(regx)

完整代码：import xlwings as xwimport requestsfrom bs4 import BeautifulSoupfrom datetime import datetimeimport jsonimport xlwtimport xlwings as xwfrom selenium import webdriverimport timeimport pandas as pdimport csvimport refrom selenium.webdrive

加载selenium控件：pip intall selenium；pip showseleniumweb下载地址：chrome浏览器,chrome插件,谷歌浏览器下载,谈笑有鸿儒 (chromedownloads.net)https://www.chromedownloads.net/

完整代码：import jsonimport requestsfrom bs4 import BeautifulSoupimport csvimport pandas as pdwith open('web.html','r',encoding='gbk') as f: html=BeautifulSoup(f,'html.parser') html.list=html.find_all('div',attrs={'class':'e'}) # print(html)

好买网完整代码：from unicodedata import decimalimport requestsfrom bs4 import BeautifulSoupfrom datetime import datetimeimport jsonimport xlwtimport xlwings as xw# 新闻链接from numpy.core import doubleurl = ' https://i.howbuy.com/member/property/'sess

完整代码：# -*- coding: UTF-8 -*-import jsonimport requestsimport sysfrom bs4 import BeautifulSoups = requests.Session()class JD: def __init__(self, username, password): self.username = username self.password = password s

cookielib操作from http import cookiejarcookielib=cookiejar.CookieJar()

完整代码：from lxml.html import fromstringfrom bs4 import BeautifulSoupimport xlwtimport jsonwith open('rr.html' ,'r' ,encoding='utf-8') as f: # Soup = BeautifulSoup(f, 'lxml') html = BeautifulSoup(f, 'html.parser') html.list=html.find_all(

完整代码：import timefrom selenium import webdriver# sys.setProperty("webdriver.chrome.driver", "C:\\Program Files (x86)\\Google\\Chrome\\Application\\chromedriver.exe");wd = webdriver.Chrome('C:\\Program Files (x86)\\Google\\Chrome\\Application\\chrome

完整代码：在这里要感谢一下博客楼主的辛勤付出，给的账户和密码都是真实的，楼主很伟大；博客来源：https://blog.csdn.net/weixin_46192930/article/details/105135087完整代码：from urllib import requestfrom urllib import parsefrom http.cookiejar import CookieJarfrom urllib import requestfrom http.cook

完整代码：#!/usr/local/bin/python3.7"""@File : cookiejar_login.py@Time : 2020/04/05@Author : Mozili"""import urllib.requestimport urllib.parse# cookiejar用来保存cookieimport http.cookiejar# 创建一个cookiejar对象cj = http.cookiejar.CookieJar

完整代码：from bs4 import BeautifulSoupimport urllib.request as urlliburl = 'https://book.douban.com/'cookie=''headers = { 'Host':'www.douban.com', 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.

request方法：import jsonimport requestsfrom lxml import etreeimport xlwings as xwimport re# 爬取网址url ="https://hz.zu.anjuke.com/?from=navigation"# 模拟浏览器访问headers =headers={'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/\537.36 (KH

完整代码：import requestsfrom bs4 import BeautifulSoupfrom datetime import datetimeimport jsonimport xlwings as xwimport xlwtdef get_list(url): # 新闻链接 res = requests.get(url) res.encoding = 'utf-8' # 完整HTML # html = BeautifulSoup(re

完整代码：import requestsfrom bs4 import BeautifulSoupfrom datetime import datetimeimport jsonimport xlwings as xw# 新闻链接url="http://news.sina.com.cn/c/2020-10-19/doc-iiznctkc6335371.shtml"res = requests.get(url)res.encoding = 'utf-8'# 完整HTML# html

安装包：pip install beautifulsoup4完整代码：import requestsfrom bs4 import BeautifulSoupfrom datetime import datetimeimport jsonimport xlwings as xw# 新闻链接url="https://news.sina.com.cn/world/"res = requests.get(url)res.encoding = 'utf-8'# 完整HTML# h

完整代码：import jsonimport requestsfrom lxml import etreeimport xlwings as xwurl="https://shenzhen.baixing.com/jiudianfuwu/m35936-m5238/"headers={'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/\537.36 (KHTML, like Gecko) Chrome/86.0.4

代码：import jsonimport xlwtperson_data=[]#定义数组#数组赋值person_data.append({ '序号':1,'name':"小王",'age':12})#输入jsonwith open('person_data.json','w',encoding='utf-8') as f: json.dump(person_data,f,indent=1,ensure_ascii=False)# 创建一个excel对象book =

读取文本文件操作# f = open('/Users/lemonlxn/Desktop/test/files/文本.txt',mode='r',encoding='utf-8')## data = f.read()# print(data)## f.close()# with open('files/文本.txt',mode='r',encoding='utf-8') as f:# data = f.readlines()# print(data[0])wit

新建excelimport xlwings as xwapp=xw.App(visible=True,add_book=False)for dept in ("技术部","开发部","销售部"): workbook=app.books.add() workbook.save(f"./部门业绩-{dept}.xlsx")

导入xlwt导入datetime完整代码模块：import xlwtimport datetimeimport datetime as datetimestyle0 = xlwt.easyxf('font: name Times New Roman, color-index red, bold on', num_format_str='#,##0.00')style1 = xlwt.easyxf(num_format_str='D-MMM-YY')wb = xlwt.Work

简单网页制作：<!DOCTYPE html><html lang="en"><head> <meta charset="UTF-8"> <title>我要自学网</title></head><body> <h1一级标题1>这是一级标题</h1一级标题1> <h2>这是二级标题</h2> <p>这是一段

导入工具包win+r；输入cmd；输入pip install BeautifulSoup4输入pip install requests主页代码：import requests# 导入bs4套件from bs4 import BeautifulSoupnewsurl = 'http://www.baidu.com/'# 发送get请求res = requests.get(newsurl)# 设置网页编码格式，如果不设置的话会产生中文乱码，编码格式按照爬取得网页来设置re.