Python爬虫技术

Life is short, you need python.

import urllib.request
 
response = urllib.request.urlopen('http://www.baidu.com')
buff = response.read()
html = buff.decode("utf8")
print(html)
命令行中执行python baidu.py，则可以打印出获取到的网页。

import urllib.request
 
request = urllib.request.Request('http://www.baidu.com')
response = urllib.request.urlopen(request)
buff = response.read()
html = buff.decode("utf8")
print(html)

import urllib.request
import urllib.parse
 
url = 'http://www.baidu.com'
values = {'name': 'voidking','language': 'Python'}
data = urllib.parse.urlencode(values).encode(encoding='utf-8',errors='ignore')
headers = { 'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:50.0) Gecko/20100101 Firefox/50.0' }
request = urllib.request.Request(url=url, data=data,headers=headers,method='GET')
response = urllib.request.urlopen(request)
buff = response.read()
html = buff.decode("utf8")
print(html)

import urllib.request
import http.cookiejar
 
# 创建cookie容器
cj = http.cookiejar.CookieJar()
# 创建opener
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
# 给urllib.request安装opener
urllib.request.install_opener(opener)
 
# 请求
request = urllib.request.Request('http://www.baidu.com/')
response = urllib.request.urlopen(request)
buff = response.read()
html = buff.decode("utf8")
print(html)
print(cj)

import bs4
print(bs4)

import bs4
from bs4 import BeautifulSoup
 
# 根据html网页字符串创建BeautifulSoup对象
html_doc = """
html>head>title>The Dormouse's story/title>/head>
body>
p class="title">b>The Dormouse's story/b>/p>
p class="story">Once upon a time there were three little sisters; and their names were
a href="//www.jb51.net/admin/index.asp" class="sister" id="link1">Elsie/a>,
a href="//www.jb51.net/admin/index.asp" class="sister" id="link2">Lacie/a> and
a href="//www.jb51.net/admin/index.asp" class="sister" id="link3">Tillie/a>;
and they lived at the bottom of a well./p>
p class="story">.../p>
"""
soup = BeautifulSoup(html_doc)
print(soup.prettify())

print(soup.title)
print(soup.title.name)
print(soup.title.string)
print(soup.title.parent.name)
 
print(soup.p)
print(soup.p['class'])

print(soup.find_all('a'))
print(soup.find('a'))
print(soup.find(class_='title'))
print(soup.find(id="link3"))
print(soup.find('p',class_='title'))

for link in soup.find_all('a'):
    print(link.get('href'))

soup = BeautifulSoup(html_doc,'html.parser')

print(soup.get_text())

link_node = soup.find('a',href=re.compile(r"til"))
print(link_node)