python 代理IP
来源:互联网 发布:unity3d怎么导入fbx 编辑:程序博客网 时间:2024/06/06 13:20
#encoding=utf8import requestsfrom urllib.request import urlopenfrom bs4 import BeautifulSoupsession=requests.Session()User_Agent = 'Mozilla/5.0 (Windows NT 6.3; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0'header = {}header['User-Agent'] = User_Agenturl = 'http://www.kuaidaili.com/'req = session.get(url,headers=header)soup = BeautifulSoup(req.text,"lxml")ips = soup.findAll('tr')f = open("proxy.txt","w")for x in range(1,len(ips)):#for x in range(1,20): ip = ips[x] tds = ip.findAll("td") ip_temp = tds[0].contents[0]+"\t"+tds[1].contents[0]+"\n" # print tds[2].contents[0]+"\t"+tds[3].contents[0] f.write(ip_temp)f.close
import requestsfrom bs4 import BeautifulSoupf = open(r"E:\Users\Desktop\proxy.txt")lines = f.readlines()proxys = []proxys_new=[]for i in range(0,len(lines)): ip = lines[i].strip("\n").split("\t") proxy_host = "http://"+ip[0]+":"+ip[1] proxy_temp = {"http":proxy_host} proxys.append(proxy_temp)url = "http:"for proxy in proxys: try: page=requests.get(url, proxies=proxy,timeout=1) bs=BeautifulSoup(page.text,"lxml") if bs.h1.get_text()=='': proxys_new.append(proxy) except Exception : print (proxy) continueimport requestsfrom bs4 import BeautifulSoupproxies = { "http": "http://112.229.101.90:8118"} page=requests.get("http://www.poi86.com/poi/amap/40.html", proxies=proxies)bs=BeautifulSoup(page.text,"lxml")print(bs)import socksimport socketsocks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, "127.0.0.1", 8787)socket.socket = socks.socksocketimport requestspage=requests.get("http://www.google.com.hk/")bs=BeautifulSoup(page.text,"lxml")print(bs)print (requests.get('http://www.google.com'))
0 0
- python 代理IP
- Python 爬虫IP代理
- python获取代理IP
- python IP代理爬虫,download 代理IP
- python 自动抓取代理ip
- Python爬取代理IP
- python动态抓取代理IP
- python多线程筛选代理ip
- python趣事-3-ip代理
- Python爬取代理IP
- python 爬虫获取代理Ip
- 【Python脚本】-Python查找可用代理IP
- IP代理池的Python实现
- python使用ip代理抓取网页
- Python爬虫设置代理IP爬取知乎图片
- python开源IP代理池--IPProxys
- Python爬虫技巧---设置代理IP
- python 爬虫 批量获取代理ip
- python dbscan算法
- 354RussianDollEnvelopes
- 管理学-控制
- 矩阵
- 简单的试图3
- python 代理IP
- Codeforces Round #376 (Div. 2) (A.B.C)
- 数组最大能开导多少
- 表单格式
- 《TC训练赛一》题解!
- Sublime Text 3安装package
- 埃拉托色尼素数筛法
- 关于AlertDialog中嵌入Edittext无法弹出输入法的问题解决
- AsyncTask的使用