tanjunchen的博客

import sysimport rep = re.compile(r'\w+')for line in sys.stdin: ss = line.strip().split(' ') for s in ss: if len(p.findall(s)) < 1: continue s_low = p.findall(s)[0].lower() print(s_low + ',' + '1')im.

python 爬取 csdn 网站信息完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/csdn#!/usr/bin/env python# -*- coding: utf-8 -*-import requestsfrom bs4 import BeautifulSoupimport multiprocessingimport timesuccess_num = 0CONSTANT = 0d.

python 爬取全国农产品批发指数网站charles 抓取 flash 数据包 分析数据包数据amf 数据请求与返回格式 flash 数据完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/agriculture#!/usr/bin/env python# -*- coding: utf-8 -*-import requestsimport uuidimport pyamfimport da..

python 获取东方财富网站的数据完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/EastWealthWebsite#!/usr/bin/env python# -*- coding: utf-8 -*-import pandas as pdfrom selenium import webdriverfrom selenium.webdriver.support import expected_cond.

Python 爬虫处理字体加密完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/fontfaceDecrypt汽车之家：#!/usr/bin/env python# -*- coding: utf-8 -*-import requestsfrom lxml import etreeimport reimport sysimport iofrom fontTools.ttLib import TTFont

Python 分布式爬取 InfoQ 信息完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/InfoQ#!/usr/bin/env python# -*- coding: utf-8 -*-import jsonimport datetimeimport timeimport randomfrom InfoQ.tool.header import headersimport requestsfrom In

python 爬取 全网代理 IP 网站完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/IP#!/usr/bin/env python# -*- coding: utf-8 -*-from lxml import etreeimport requestsdef spider(): url = 'http://www.goubanjia.com/' headers = { 'A

python 爬取 IT 桔子网完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/ITOrangeimport requestsimport reimport pymongoimport randomimport timeimport jsonimport randomimport numpy as npimport csvimport pandas as pdfrom fake_useragent i

python selenium 爬取去哪儿网的数据完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/selenium+qunaerwang#!/usr/bin/python# -*- coding: UTF-8 -*-from selenium import webdriverimport datetimefrom selenium.webdriver.support.ui import WebDriverWai

python 爬取拉钩网数据完整代码下载：https://github.com/tanjunchen/SpiderProject/blob/master/lagou/LaGouSpider.py#!/usr/bin/env python# -*- coding: utf-8 -*-import randomimport timeimport requestsfrom openpyxl import Workbookimport pymysql.cursorsdef get_c

python mitmproxy 使用案例完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/mitmproxyspider#!/usr/bin/env python# -*- coding: utf-8 -*-from mitmproxy import ctx, flowdef job(url): injected_javascript = ''' // overwrite the `la..

python 模拟人为行为登录 zcool 站酷网站完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/zcool#!/usr/bin/env python# -*- coding: utf-8 -*-from selenium import webdriverfrom selenium.webdriver.support.wait import WebDriverWaitfrom selenium.webdriv

完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/qimingpian#!/usr/bin/env python# -*- coding: utf-8 -*-import execjsimport base64import jsonimport requestsheaders = { 'Accept': 'application/json, text/plain, */*', 'Content-

微信助手 itchat 小工具的使用完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/wechartrobot#!/usr/bin/env python# -*- coding: utf-8 -*-import osimport requestsimport itchatfrom itchat.content import *import timefrom apscheduler.schedulers.ba

完整代码下载：https://github.com/tanjunchen/SpiderProject/blob/master/tourongzi/Spider.py#!/usr/bin/python# -*- coding: UTF-8 -*-import requestsfrom fake_useragent import UserAgentimport pandas as pdfrom lxml import etreeimport reua = UserAgent().

完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/wwwtzxmgovcn投资项目在线审批监管平台# !/usr/bin/env python# -*- coding: utf-8 -*-import requestsimport pandas as pdimport randomimport timefrom requests.packages.urllib3.exceptions import Insec

python 爬取中国木材价格指数网完整代码：https://github.com/tanjunchen/SpiderProject/tree/master/yuzhuprice#!/usr/bin/env python# -*- coding: utf-8 -*-from datetime import datetimefrom concurrent.futures.thread import ThreadPoolExecutorfrom multiprocessing impo.

python 爬取自如租房的租房数据完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/ziru#!/usr/bin/python# -*- coding: UTF-8 -*-import reimport requestsimport pytesseractfrom PIL import Imagefrom selenium import webdriverfrom fake_useragent impor

python 爬取康美中药网站完整代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/kangmeizhongyao#!/usr/bin/env python# -*- coding: utf-8 -*-import requestsfrom lxml import etreeimport jsonimport pandas as pdimport datetimefrom kangmeizhongyao..

源代码下载：https://github.com/tanjunchen/SpiderProject/tree/master/ZipCode中国邮政编码http://www.yb21.cn#!/usr/bin/env python# -*- coding: utf-8 -*-import jsonfrom lxml import etreefrom multiprocessing import Manager, cpu_count, Poolimport requestsfr.

前段时间逛博客的时候，看到了Alex总结的Python题目，目前在自学Python，想要检测下效果，所以总结并完善相关答案。1：为什么学习Python？语言本身简洁，优美，功能超级强大，跨平台，桌面应用，web开发，自动化测试运维，爬虫，人工智能，大数据处理。本人是从Python爬虫开始学的。2：Python和Java、PHP、C、C#、C++等其他语言的对比？Java 编程语言是...