資源簡介
ip.py 自動檢索出可用代理ip port的python腳本,需要 python 3.x ip.py 自動檢索出可用代理ip port的python腳本,需要 python 3.x
代碼片段和文件信息
#!/usr/bin/env?python3
#?-*-?coding:?utf-8?-*-
import?requeststhreadingdatetime
from?bs4?import?BeautifulSoup
import?random
“““
1、抓取西刺代理網站的代理ip
2、并根據指定的目標url對抓取到ip的有效性進行驗證
3、最后存到指定的path
“““
#?------------------------------------------------------文檔處理--------------------------------------------------------
#?寫入文檔
def?write(pathtext):
????with?open(path‘a‘?encoding=‘utf-8‘)?as?f:
????????f.writelines(text)
????????f.write(‘\n‘)
#?清空文檔
def?truncatefile(path):
????with?open(path?‘w‘?encoding=‘utf-8‘)?as?f:
????????f.truncate()
#?讀取文檔
def?read(path):
????with?open(path?‘r‘?encoding=‘utf-8‘)?as?f:
????????txt?=?[]
????????for?s?in?f.readlines():
????????????txt.append(s.strip())
????return?txt
#?----------------------------------------------------------------------------------------------------------------------
#?計算時間差格式:?時分秒
def?gettimediff(startend):
????seconds?=?(end?-?start).seconds
????m?s?=?divmod(seconds?60)
????h?m?=?divmod(m?60)
????diff?=?(“%02d:%02d:%02d“?%?(h?m?s))
????return?diff
#?----------------------------------------------------------------------------------------------------------------------
#?返回一個隨機的請求頭?headers
def?getheaders():
????user_agent_list?=?[?\
????????“Mozilla/5.0?(Windows?NT?6.1;?WOW64)?AppleWebKit/537.1?(KHTML?like?Gecko)?Chrome/22.0.1207.1?Safari/537.1“?\
????????“Mozilla/5.0?(X11;?CrOS?i686?2268.111.0)?AppleWebKit/536.11?(KHTML?like?Gecko)?Chrome/20.0.1132.57?Safari/536.11“?\
????????“Mozilla/5.0?(Windows?NT?6.1;?WOW64)?AppleWebKit/536.6?(KHTML?like?Gecko)?Chrome/20.0.1092.0?Safari/536.6“?\
????????“Mozilla/5.0?(Windows?NT?6.2)?AppleWebKit/536.6?(KHTML?like?Gecko)?Chrome/20.0.1090.0?Safari/536.6“?\
????????“Mozilla/5.0?(Windows?NT?6.2;?WOW64)?AppleWebKit/537.1?(KHTML?like?Gecko)?Chrome/19.77.34.5?Safari/537.1“?\
????????“Mozilla/5.0?(X11;?Linux?x86_64)?AppleWebKit/536.5?(KHTML?like?Gecko)?Chrome/19.0.1084.9?Safari/536.5“?\
????????“Mozilla/5.0?(Windows?NT?6.0)?AppleWebKit/536.5?(KHTML?like?Gecko)?Chrome/19.0.1084.36?Safari/536.5“?\
????????“Mozilla/5.0?(Windows?NT?6.1;?WOW64)?AppleWebKit/536.3?(KHTML?like?Gecko)?Chrome/19.0.1063.0?Safari/536.3“?\
????????“Mozilla/5.0?(Windows?NT?5.1)?AppleWebKit/536.3?(KHTML?like?Gecko)?Chrome/19.0.1063.0?Safari/536.3“?\
????????“Mozilla/5.0?(Macintosh;?Intel?Mac?OS?X?10_8_0)?AppleWebKit/536.3?(KHTML?like?Gecko)?Chrome/19.0.1063.0?Safari/536.3“?\
????????“Mozilla/5.0?(Windows?NT?6.2)?AppleWebKit/536.3?(KHTML?like?Gecko)?Chrome/19.0.1062.0?Safari/536.3“?\
????????“Mozilla/5.0?(Windows?NT?6.1;?WOW64)?AppleWebKit/536.3?(KHTML?like?Gecko)?Chrome/19.0.1062.0?Safari/536.3“?\
????????“Mozilla/5.0?(Windows?NT?6.2)?AppleWebKit/536.3?(KHTML?like?Gecko)?Chrome/19.0.1061.1?Safari/536.3“?\
????????“Mozilla/5.0?(Windows?NT?6.1;?WOW64)?AppleWebKit/536.3?(KHTML?like?Gecko)?Chrome/19.0.1061.1?Safari/536.3“?\
????????“Mozilla/5.0?(Windows?NT?6.1)?AppleWebKit/536.3?(KHTML?l
- 上一篇:百度遷徙數據爬取
- 下一篇:python多目標優化求解
評論
共有 條評論