Python开发之爬虫模块介绍（一）

时间 2019-11-11

原文原文链接

Urllib库

Urllib是Python内置的HTTP请求库，包括了4个模块：html

urllib.request 请求模块
urllib.error 异常处理模块
urllib.parse url解析模块
urllib.robotparser robots.txt解析模块

一、urllib.request 的urlopen()python

import urllib.request

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

response = urllib.request.urlopen('http://httpbin.org/get',timeout=1) # 设置超时时间
print(response.read())

import urllib.request
import socket
import urllib.error
try:
    response = urllib.request.urlopen('http://httpbin.org/get',timeout=0.1)
except urllib.error.URLError as e:
    if isinstance(e.reason,socket.timeout):
        print('TIME OUT')

二、响应nginx

响应类型

import urllib.request

response = urllib.request.urlopen('http://www.baidu.com')
print(type(response)) # <class 'http.client.HTTPResponse'>

状态码、响应头

import urllib.request

response = urllib.request.urlopen('http://www.python.org')
print(response.status) # 200
print(response.getheaders())
print(response.getheader('Server')) #nginx

三、urllib.request.Request()git

from urllib import request,parse

url = 'http://httpbin.org/post'

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
    'Host':'httpbin.org'
}

dict = {
    'name':'Germey'
}

data = bytes(parse.urlencode(dict),encoding='utf8')
req = request.Request(url=url,data=data,headers=headers,method='POST') # 是一个object
response = request.urlopen(req)
print(response.read().decode('utf8'))

利用request.Request()方法能够灵活的构造要请求的内容和类型github

还能够利用.add_header()方法来添加headersjson

from urllib import request,parse

url = 'http://httpbin.org/post'

dict = {
    'name':'Germey'
}

data = bytes(parse.urlencode(dict),encoding='utf8')
req = request.Request(url=url,data=data,method='POST') # 是一个object
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) ') 
response = request.urlopen(req)
print(response.read().decode('utf8'))

四、urllib.request.ProxyHandler()实现代理cookie

import urllib.request

proxy_handler = urllib.request.ProxyHandler({
    'http':'http://127.0.0.1:9743',
    'https':'https://127.0.0.1:9743',
})

opener = urllib.request.build_opener(proxy_handler)
response = opener.open('http://httpbin.org/get')
print(response.read())

五、cookiessession

import http.cookiejar,urllib.request

cookie = http.cookiejar.CookieJar()
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler) # 也是代理的一种新式
response = opener.open('http://www.baidu.com')
for item in cookie:
    print(item.name + '='+ item.value)

'''
BAIDUID=A980763F2538BCB3FDA9E5BC979758CB:FG=1
BIDUPSID=A980763F2538BCB3FDA9E5BC979758CB
H_PS_PSSID=1453_26909_21094_18559_26350
PSTM=1533972705
BDSVRTM=0
BD_HOME=0
delPer=0
'''

把cookie保存成文本文件socket

import http.cookiejar,urllib.request
filename = 'cookie.txt'
cookie = http.cookiejar.MozillaCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler) # 也是代理的一种新式
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True,ignore_expires=True)

六、异常处理post

from urllib import request,error

try:
    response = urllib.request.urlopen('http://cuiqingcai/index.html')
except error.URLError as e:
    print(e.reason) #[Errno 11004] getaddrinfo failed

from urllib import request,error

try:
    response = urllib.request.urlopen('http://cuiqingcai/index.html')
except error.HTTPError as e:
    print(e.reason,e.code,e.headers,sep='\n') #[Errno 11004] getaddrinfo failed
except error.URLError as e:
    print(e.reason)
else:
    print('Request successful')

先捕获HTTPError，再捕获URLError。

七、URL解析

from urllib.parse import urlparse

result = urlparse('https://www.suning.com/?vip_frm=super_nav_vip')
print(type(result),result)
'''
<class 'urllib.parse.ParseResult'> ParseResult(scheme='https', netloc='www.suning.com', path='/', params='', query='vip_frm=super_nav_vip', fragment='')
'''
# 把url进行标准的拆分

八、urlencode 能够将字典转换为get请求的参数

from urllib.parse import urlencode

params = {
    'name':'germay',
    'age':'12'
}

base_url = 'http://www.baidu.com?'
url = base_url + urlencode(params)
print(url) #http://www.baidu.com?name=germay&age=12

Requests库

requests库相比urllib库来讲，比urllib库要方便许多，先来简单体验一下

import requests

response = requests.get('http://www.baidu.com')
print(response) # 200
print(response.status_code)
print(type(response.text),response.text) #<class 'str'>
print(response.cookies) # <RequestsCookieJar[<Cookie BDORZ=27315 for .baidu.com/>]>

一、requests库的各类请求方式

import requests
print(requests.get('http://httpbin.org/get'))
print(requests.post('http://httpbin.org/post'))
print(requests.delete('http://httpbin.org/delete'))
print(requests.put('http://httpbin.org/put'))
print(requests.options('http://httpbin.org/get'))
print(requests.head('http://httpbin.org/get'))

二、get请求

import requests
response = requests.get('http://httpbin.org/get')
print(response.text)
'''
{
  "args": {}, 
  "headers": {
    "Accept": "*/*", 
    "Accept-Encoding": "gzip, deflate", 
    "Connection": "close", 
    "Host": "httpbin.org", 
    "User-Agent": "python-requests/2.18.4"
  }, 
  "origin": "113.59.106.145", 
  "url": "http://httpbin.org/get"
}
'''

三、带参数的get请求

import requests
response = requests.get('http://httpbin.org/get?name=germay&age=22')
print(response.text)
'''
{
  "args": {
    "age": "22", 
    "name": "germay"
  }, 
  "headers": {
    "Accept": "*/*", 
    "Accept-Encoding": "gzip, deflate", 
    "Connection": "close", 
    "Host": "httpbin.org", 
    "User-Agent": "python-requests/2.18.4"
  }, 
  "origin": "113.59.106.145", 
  "url": "http://httpbin.org/get?name=germay&age=22"
}
'''

import requests
data = {
   'name':'germay',
    'age':22
}
response = requests.get('http://httpbin.org/get',params=data)
print(response.text)

四、json解析

import requests
import json
response = requests.get('http://httpbin.org/get')
print(response.json())
print(json.loads(response.text))
'''
{'args': {}, 'headers': {'Accept': '*/*', 'Accept-Encoding': 'gzip, deflate', 'Connection': 'close', 'Host': 'httpbin.org', 'User-Agent': 'python-requests/2.18.4'}, 'origin': '113.59.106.145', 'url': 'http://httpbin.org/get'}
{'args': {}, 'headers': {'Accept': '*/*', 'Accept-Encoding': 'gzip, deflate', 'Connection': 'close', 'Host': 'httpbin.org', 'User-Agent': 'python-requests/2.18.4'}, 'origin': '113.59.106.145', 'url': 'http://httpbin.org/get'}
'''

response.json()和json.loads(response.text)同样。

五、获取二进制数据

import requests
response = requests.get('https://github.com/favicon.ico')
print(type(response.text)) #<class 'str'>
print(type(response.content))  #<class 'bytes'>

.text是str类型，.content是bytes类型

import requests
response = requests.get('https://github.com/favicon.ico')
print(type(response.text)) #<class 'str'>
print(type(response.content))  #<class 'bytes'>

with open('favicon.ico','wb') as f:
    f.write(response.content)

六、添加headers

不加header爬取知乎的结果

import requests
response = requests.get('https://www.zhihu.com/explore')
print(response.text)
'''
<html>
<head><title>400 Bad Request</title></head>
<body bgcolor="white">
<center><h1>400 Bad Request</h1></center>
<hr><center>openresty</center>
</body>
</html> 
'''

加headers爬取知乎的结果：是完整的这个页面

import requests
headers = {
    'user-agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
}
response = requests.get('https://www.zhihu.com/explore',headers=headers)
print(response.text)

因此，在网页爬取时，添加headers是很是必要的，不加的话极可能被禁掉。

七、响应

response属性

import requests
headers = {
    'user-agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
}
response = requests.get('https://www.zhihu.com/explore',headers=headers)
print(response.status_code) # 200
print(response.headers)
print(response.cookies)
print(response.url) #https://www.zhihu.com/explore
print(response.history)

八、文件上传

import requests

files = {"file":open('favicon.ico','rb')}

response = requests.post('http://httpbin.org/post',files=files)
print(response.text)

九、获取cookie

import requests

response = requests.get('https://www.baidu.com')
print(response.cookies)
for k,v in response.cookies.items():
    print(k+'='+v)

十、会话维持

import requests

s = requests.session()
s.get('http://httpbin.org/cookies/set/number/1122112')
response = s.get('http://httpbin.org/cookies')
print(response.text)
'''
{
  "cookies": {
    "number": "1122112"
  }
}
'''

十一、证书验证

import requests

response = requests.get('https://www.12306.cn')
print(response.status_code) #requests.exceptions.SSLError

上述代码访问12306直接报SSLError错误

若是加上verify=False,就能够正常爬取

import requests
from requests.packages import urllib3
urllib3.disable_warnings() # 消除警告的做用
response = requests.get('https://www.12306.cn',verify=False)
print(response.status_code) #requests.exceptions.SSLError

十二、代理

import requests
proxy = ({
    'http':'http://127.0.0.1:9743',
    'https':'https://127.0.0.1:9743',
})

response = requests.get('https://www.taobao.com',proxies=proxy)
print(response.status_code)

1三、超时设置

import requests

response = requests.get('https://www.taobao.com',timeout=1)
print(response.status_code)

1四、认证设置

对于一些须要登陆才能访问的网站，须要进行认证处理

import requests

response = requests.get('https://127.27.34.24:9001',auth=('user','123'))
print(response.status_code)

1五、异常处理

import requests
from requests.exceptions import ReadTimeout,HTTPError,RequestException
try:
    response = requests.get('https://www.taobao.com',timeout=1)
    print(response.status_code)
except ReadTimeout:
    print('Timeout')
except HTTPError:
    print('Http error')
except RequestException:
    print('error')