【python】如何把爬取到的代理ip写入到mongoDB

之前的 博文 是把代理ip写入到txt文件中，然而真实情景中，写入数据比较方便以后调用。

还和之前一样，我先把我遇到的问题说一下：

1.这里必须先安装 pymongo，选择以下其中一种即可，我用的是pip install --upgrade pymongo

2.然后数据库更新后手动刷一下才看到新的数据

# 安装

pip install pymongo

# 升级

pip install --upgrade pymongo

这里先看一个简单的例子，数据是如何写入到mongoDB的： 

import pymongo
from pymongo import MongoClient
#1.链接本地数据库服务
name = MongoClient('localhost')
#2.链接本地数据库 demo 没有会创建
db = name.demo   #demo数据库名
#3.创建，连接集合
emp = db.employees  #employees集合名
#4.根据情况清空聚合
emp.remove(None)
#emp.delete_one()
#emp.delete_many({})
#5.创建一条数据
zhangsan = {
    'name':'张三',
    'age':30,
    'sex':'男',
    'contect':{
    'email':'abc@qq.com',
    'phine':'12345678910'
    }
}
#5.1增加一条数据
emp.insert_one(zhangsan)
#5.2增加多条数据
emp.insert_many([
    {
    'name':'李四',
    'habit':{
        'habit1':'eat',
        'habit2':'sleep'
        }
    },
    {
    'name':'王五',
    'age':20,
    'sex':'男'
    },
    {
    'name':'张三丰',
    'age':100,
    'sex':'男',
    'contect':{
    'email':'abcdef@qq.com',
    'phine':'12345678910'
    }}
])

下面是我实现的代码（原本用于存于txt文件的代码我没注释掉 ，只注释了调用）：

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import requests,threading,datetime
from bs4 import BeautifulSoup
import random
import pymongo
from pymongo import MongoClient

"""
1、抓取西刺代理网站的代理ip
2、并根据指定的目标url,对抓取到ip的有效性进行验证
3、最后存到指定的path
"""
# ------------------------------------------------------数据处理--------------------------------------------------------
#1.链接本地数据库服务
name = MongoClient('localhost')
#2.链接本地数据库 demo 没有会创建
db = name.demo   #demo数据库名
#3.创建，连接集合
emp = db.employees  #employees集合名
#4.根据情况清空聚合
emp.remove(None)
def writeData(path,text):
    emp.insert_one({'ip':text})


# ------------------------------------------------------文档处理--------------------------------------------------------
# 写入文档
def write(path,text):
    with open(path,'a', encoding='utf-8') as f:
        f.writelines(text)
        f.write('\n')
# 清空文档
def truncatefile(path):
    with open(path, 'w', encoding='utf-8') as f:
        f.truncate()
# 读取文档
def read(path):
    with open(path, 'r', encoding='utf-8') as f:
        txt = []
        for s in f.readlines():
            txt.append(s.strip())
    return txt
# ----------------------------------------------------------------------------------------------------------------------
# 计算时间差,格式: 时分秒
def gettimediff(start,end):
    seconds = (end - start).seconds
    m, s = divmod(seconds, 60)
    h, m = divmod(m, 60)
    diff = ("%02d:%02d:%02d" % (h, m, s))
    return diff
# ----------------------------------------------------------------------------------------------------------------------
# 返回一个随机的请求头 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, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", \
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", \
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
    ]
    UserAgent=random.choice(user_agent_list)
    headers = {'User-Agent': UserAgent}
    return headers
# -----------------------------------------------------检查ip是否可用----------------------------------------------------
def checkip(targeturl,ip):
    headers =getheaders()  # 定制请求头
    proxies = {"http": "http://"+ip, "https": "http://"+ip}  # 代理ip
    try:
        response=requests.get(url=targeturl,proxies=proxies,headers=headers,timeout=5).status_code
        if response == 200 :
            return True
        else:
            return False
    except:
        return False

#-------------------------------------------------------获取代理方法----------------------------------------------------
# 免费代理 XiciDaili
def findip(type,pagenum,targeturl,path): # ip类型,页码,目标url,存放ip的路径
    list={'1': 'http://www.xicidaili.com/nt/', # xicidaili国内普通代理
          '2': 'http://www.xicidaili.com/nn/', # xicidaili国内高匿代理
          '3': 'http://www.xicidaili.com/wn/', # xicidaili国内https代理
          '4': 'http://www.xicidaili.com/wt/'} # xicidaili国外http代理
    url=list[str(type)]+str(pagenum) # 配置url
    headers = getheaders() # 定制请求头
    html=requests.get(url=url,headers=headers,timeout = 5).text
    soup=BeautifulSoup(html,'lxml')
    all=soup.find_all('tr',class_='odd')
    for i in all:
        t=i.find_all('td')
        ip=t[1].text+':'+t[2].text
        is_avail = checkip(targeturl,ip)
        if is_avail == True:
            # write(path=path,text=ip)
            writeData(path=path, text=ip)
            print(ip)

#-----------------------------------------------------多线程抓取ip入口---------------------------------------------------
def getip(targeturl,path):
     # truncatefile(path) # 爬取前清空文档
     start = datetime.datetime.now() # 开始时间
     threads=[]
     for type in range(4):   # 四种类型ip,每种类型取前1页
         for pagenum in range(1):
             t=threading.Thread(target=findip,args=(type+1,pagenum+1,targeturl,path))
             threads.append(t)
     print('开始爬取代理ip')
     for s in threads: # 开启多线程爬取
         s.start()
     for e in threads: # 等待所有线程结束
         e.join()
     print('爬取完成')
     end = datetime.datetime.now() # 结束时间
     diff = gettimediff(start, end)  # 计算耗时
     # ips = read(path)  # 读取爬到的ip数量
     # print('一共爬取代理ip: %s 个,共耗时: %s \n' % (len(ips), diff))

#-------------------------------------------------------启动-----------------------------------------------------------
if __name__ == '__main__':
    path = 'ip.txt' # 存放爬取ip的文档path
    targeturl = 'http://www.cnblogs.com/TurboWay/' # 验证ip有效性的指定url
    getip(targeturl,path)

效果如下：

参考：

• python读取MongoDB
• python更新MongoDB
• python删除MongoDB