python3爬虫环境搭建

安装python3

sudo apt-get install python3-dev build-essential libssl-dev libffi-dev libxml2 libxml2-dev libxslt1-dev zlib1g-dev
sudo apt-get install python3
sudo apt-get install ptyhon3-pip

ubuntu安装mongo

sudo apt-get install mongodb
mongod
mongo
> show dbs
admin  (empty)
local  0.078GB
> use local
switched to db local
> db.test.insert({'a':'b'})
WriteResult({ "nInserted" : 1 })

mac安装mongo

brew install mongodb
brew services start mongodb

ubuntu安装redis

sudo apt-get install redis-server
redis-cli
127.0.0.1:6379> set 'a' 'b'
OK
127.0.0.1:6379> get 'a'
"b"
127.0.0.1:6379> 
root@iZwz91u9ywulp6n78yyed6Z:~# sudo vi /etc/redis/redis.conf 
requirepass myredisserver
sudo service redis restart
root@iZwz91u9ywulp6n78yyed6Z:~# redis-cli -a myredisserver
127.0.0.1:6379> get 'a'
"b"
127.0.0.1:6379> 

mac 安装redis

brew install redis
qunzhudeMacBook-Air:/ qunzhupu$ brew services start redis
==> Successfully started `redis` (label: homebrew.mxcl.redis)
qunzhudeMacBook-Air:/ qunzhupu$ redis-cli
127.0.0.1:6379> set 'a' 'b'
OK
127.0.0.1:6379> get 'a'
"b"
cd /usr/local/etc
sudo vim redis.conf
requirepass foobared

ubuntu配置mysql

root@iZwz91u9ywulp6n78yyed6Z:~# cd /etc/mysql/
root@iZwz91u9ywulp6n78yyed6Z:/etc/mysql# ls
conf.d  debian.cnf  debian-start  my.cnf  my.cnf.fallback  mysql.cnf  mysql.conf.d
root@iZwz91u9ywulp6n78yyed6Z:/etc/mysql# cd mysql.conf.d/
root@iZwz91u9ywulp6n78yyed6Z:/etc/mysql/mysql.conf.d# ls
mysqld.cnf  mysqld_safe_syslog.cnf
root@iZwz91u9ywulp6n78yyed6Z:/etc/mysql/mysql.conf.d# vi mysqld.cnf 
root@iZwz91u9ywulp6n78yyed6Z:/etc/mysql/mysql.conf.d# sudo service mysql restart
GRANT ALL PRIVILEGES ON *.* TO 'root'@'%' IDENTIFIED BY '123456' WITH GRANT OPTION;
FLUSH PRIVILEGES;

selenium库使用

>>> import selenium
>>> from selenium import webdriver
>>> driver - webdriver.Chrome()
>>> driver.get('http://www.baidu.com')

安装beautifulsoup4和pyquery

pip3 install beautifulsoup4
pip3 install pyquery
qunzhudeMacBook-Air:bin qunzhupu$ python3
Python 3.7.0 (default, Jun 29 2018, 20:13:13) 
[Clang 9.1.0 (clang-902.0.39.2)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> from pyquery import PyQuery as pq
>>> dec =pq('<html></html>')
>>> dec =pq('<html>Hello</html>')
>>> result = dec('html').text()
>>> result
'Hello'
>>> 

pymysql连接Mysql

qunzhudeMacBook-Air:bin qunzhupu$ python3
Python 3.7.0 (default, Jun 29 2018, 20:13:13) 
[Clang 9.1.0 (clang-902.0.39.2)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> import pymysql
>>> conn = pymysql.connect(host='123.206.204.80',user='puqunzhu',password='123456',port=3306,db='puqunzhu')
>>> cursor = conn.cursor()
>>> cursor.execute('select * from article')
1

pymongo连接mongoDB

pip3 install pymongo
qunzhudeMacBook-Air:bin qunzhupu$ python3
Python 3.7.0 (default, Jun 29 2018, 20:13:13) 
[Clang 9.1.0 (clang-902.0.39.2)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> import pymongo
>>> client = pymongo.MongoClient('localhost')
>>> db = client['newtestdb']
>>> db['table'].insert({'name':'Bob'})
__main__:1: DeprecationWarning: insert is deprecated. Use insert_one or insert_many instead.
ObjectId('5bc5b059e18a3620cc46bdb4')
>>> db['table'].find_one({'name':'Bob'})
{'_id': ObjectId('5bc5b059e18a3620cc46bdb4'), 'name': 'Bob'}

redis连接redis

pip3 install redis
qunzhudeMacBook-Air:bin qunzhupu$ python3
Python 3.7.0 (default, Jun 29 2018, 20:13:13) 
[Clang 9.1.0 (clang-902.0.39.2)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> import redis
>>> r = redis.Redis('localhost',6379)
>>> r.set('name','puqunzhu')
True
>>> r.get('name')
b'puqunzhu'

flask代理获取

pip3 install flask

django

pip3 install django

jupyter

pip3 install jupyter
qunzhudeMacBook-Air:bin qunzhupu$ jupyter notebook
大道理谁都懂,鸡汤也听过,可我们为什么还是过不好这一生。
原文地址:https://www.cnblogs.com/puqunzhu/p/9799816.html