AKever

导航

网络爬虫python入门基础篇

网络爬虫python入门基础篇

 

# 1 url
# ========================================

import urllib.request

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

 

# 2 携带参数
# ========================================

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)

 

# 3 添加处理器
# ========================================

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)

 

# 4 install 网页解析器（BeautifulSoup）
# ========================================

sudo apt-get install python3-pip
sudo pip3 install beautifulsoup4
import bs4
print(bs4)

 

# 5 install 网页解析器（BeautifulSoup）
# ========================================

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="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" 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())

 

# 6 网页解析器（BeautifulSoup）soup.
# # ========================================

# 2、访问节点
print(soup.title)
print(soup.title.name)
print(soup.title.string)
print(soup.title.parent.name)

print(soup.p)
print(soup.p['class'])
# 3、指定tag、class或id

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'))
# 4、从文档中找到所有<a>标签的链接
for link in soup.find_all('a'):
    print(link.get('href'))

 

posted on 2018-12-24 14:47  AKever  阅读(110)  评论(0)    收藏  举报