实例讲解Python爬取网页数据

>>> import webbrowser 
>>> webbrowser.open('http://i.firefoxchina.cn/?from=worldindex') 
True 

#! python3 
import webbrowser, sys, pyperclip 
if len(sys.argv) > 1: 
 mapAddress = ''.join(sys.argv[1:]) 
else: 
 mapAddress = pyperclip.paste() 
webbrowser.open('http://map.baidu.com/?newmap=1&ie=utf-8&s=s%26wd%3D' + mapAddress 

>>> import requests 
>>> res = requests.get('http://i.firefoxchina.cn/?from=worldindex') #向get中传入一个网址 
>>> type(res) #响应对象 
<class 'requests.models.Response'> 
>>> print(res.status_code) #响应码 
200 
>>> res.text #返回的文本 

import requests 
res = requests.get('http://i.firefoxchina.cn/?from=worldindex') 
try: 
 res.raise_for_status() 
except Exception as exc: 
 print('There was a problem: %s' % (exc)) 

>>> import requests 
>>> res = requests.get('http://tech.firefox.sina.com/17/0820/10/6DKQALVRW5JHGE1I.html##0-tsina-1-13074-397232819ff9a47a7b7e80a40613cfe1') 
>>> res.raise_for_status() 
>>> file = open('1.txt', 'wb') #以写二进制模式打开文件，目的是保存文本中的“Unicode编码” 
>>> for word in res.iter_content(100000): #<span class="fontstyle0"><span class="fontstyle0">iter_content()</span><span class="fontstyle1">方法在循环的每次迭代中返回一段</span><span class="fontstyle0">bytes</span><span class="fontstyle1">数据</span><span class="fontstyle1">类型的内容，你需要指定其包含的字节数</span></span> 
 file.write(word) 
 
 
16997 
>>> file.close() 

>>> import requests, bs4 
>>> res = requests.get('http://i.firefoxchina.cn/?from=worldindex') 
>>> res.raise_for_status() 
>>> soup = bs4.BeautifulSoup(res.text) 
 
Warning (from warnings module): 
 File "C:\Users\King\AppData\Local\Programs\Python\Python36-32\lib\site-packages\beautifulsoup4-4.6.0-py3.6.egg\bs4\__init__.py", line 181 
 markup_type=markup_type)) 
UserWarning: No parser was explicitly specified, so I'm using the best available HTML parser for this system ("html.parser"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently. 
 
The code that caused this warning is on line 1 of the file <string>. To get rid of this warning, change code that looks like this: 
 
 BeautifulSoup(YOUR_MARKUP}) 
 
to this: 
 
 BeautifulSoup(YOUR_MARKUP, "html.parser") 
 
>>> soup = bs4.BeautifulSoup(res.text, 'html.parser') 
>>> type(soup) 
<class 'bs4.BeautifulSoup'> 

>>> import bs4 
>>> html = open('C:\\Users\\King\\Desktop\\1.htm') 
>>> exampleSoup = bs4.BeautifulSoup(html) 
>>> exampleSoup = bs4.BeautifulSoup(html, 'html.parser') 
>>> type(exampleSoup) 
<class 'bs4.BeautifulSoup'> 

>>> import requests, bs4 
>>> res = requests.get('http://i.firefoxchina.cn/?from=worldindex') 
>>> res.raise_for_status() 
>>> soup = bs4.BeautifulSoup(res.text, 'html.parser') 
>>> author = soup.select('#author') 
>>> print(author) 
[] 
>>> type(author) 
<class 'list'> 
>>> link = soup.select('link ') 
>>> print(link) 
[<link href="css/mozMainStyle-min.css?v=20170705" rel="external nofollow" rel="external nofollow" rel="stylesheet" type="text/css"/>, <link href="" id=" rel="external nofollow" rel="external nofollow" rel="external nofollow" moz-skin" rel="stylesheet" type="text/css"/>, <link href="" id=" rel="external nofollow" rel="external nofollow" rel="external nofollow" moz-dir" rel="stylesheet" type="text/css"/>, <link href="" id=" rel="external nofollow" rel="external nofollow" rel="external nofollow" moz-ver" rel="stylesheet" type="text/css"/>] 
>>> type(link) 
<class 'list'> 
>>> len(link) 
4 
>>> type(link[0]) 
<class 'bs4.element.Tag'> 
>>> link[0] 
<link href="css/mozMainStyle-min.css?v=20170705" rel="external nofollow" rel="external nofollow" rel="stylesheet" type="text/css"/> 
>>> link[0].attrs 
{'rel': ['stylesheet'], 'type': 'text/css', 'href': 'css/mozMainStyle-min.css?v=20170705'} 

>>> link[0].get('href') 
'css/mozMainStyle-min.css?v=20170705