《Python3网络爬虫开发实战》-安装Python爬虫库

urllib


import urllib

import urllib.request

urllib.request.urlopen('http://www.baidu.com')

import re

request

#请求
pip3 install request

import request

selenium

#渲染包
import selenium

from selenium import webdriver

#需手动下载chromedriver http://chromedriver.chromium.org/downloads
driver = webdriver.Chrome()

#get网页
driver.get('http://www.baidu.com')

#获取页面代码
driver.page_source
#为了避免获取网页弹出浏览器窗口,需下载phantomjs并配置PATH
#官网地址下载 http://phantomjs.org/download.html

from selenium import webdriver

drvier = webdriver.PhantomJS()

driver.get('http://www.baidu.com')

driver.page_source

lxml

#可以用pip安装
pip install lxml

#也可以下载下载 https://pypi.org/project/lxml/

import lxml

beautifulsoup4

#安装beautifulsoup4
pip3 install beautifulsoup4

#bs4是beautifulsoup4的其中一个包
from bs4 import BeautifulSoup

soup = BeautifulSoup('<html></html>','lxml')

pyquery

#pyquery相关文档 https://pythonhosted.org/pyquery/

#安装pyquery
pip3 install pyquery

from pyquery import PyQuery as pq

doc = pq('<html></html>')

doc = pq('<html>hello</html>')

result = doc('html').text()

result

'hello'


pymysql

pip3 install pymysql

import pymysql

conn = pymysql.connect(host='localhost',user='root',password='',port=3306,db='hank')

cursor = conn.cursor()

cursor.execute('select * from hank')

cursor.fetchone()

(1, 'hank', 'men', 18, '15019788915')


pymongo

pip3 install pymongodb

import pymongo

client = pymongo.MongoClient('localhost')

db = client['newtestdb']

db['table'].insert(('name':'Bob'))

db['table'].find_one(('name':'Bob'))

flask

#参考文档 http://docs.jinkan.org/docs/flask/

pip3 install flask

django

pip3 install django

import django

jupyter

pip3 install jupyter

猜你喜欢

转载自www.cnblogs.com/hankleo/p/9776442.html