爬蟲01 —— urllib庫

一、內置的請求塊

• urllib.request 請求模塊
• urllib.error 異常處理模塊
• urllib.parse url解析模塊
• urllib.robotparser robot.txt解析模塊

二、基本用法

urllib.request.urlopen(url, data=None, [timeout, ]*, cafile=None, capath=None, cadefault=False, context=None)

1、urlopen

url

import urllib.request

response = urllib.request.urlopen('http://www.baidu.com')
print(response.read().decode('utf-8')

data
字節流編碼的內容，傳遞了這個參數它將是以post方式發送、

import urllib.parse
import urllib.request

data = bytes(urllib.parse.urlencode({'word': 'hello'}), encoding='utf8')
response = urllib.request.urlopen('http://httpbin.org/post', data=data)
print(response.read())

timeout
超時異常

import urllib.request

response = urllib.request.urlopen('http://httpbin.org/get', timeout=1)
print(response.read())

import socket
import urllib.request
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')

2、response

響應類型

import urllib.request

response = urllib.request.urlopen('https://www.python.org')
print(type(response))

狀態碼和響應頭

import urllib.request

response = urllib.request.urlopen('https://www.python.org')
print(response.status)
print(response.getheaders())
print(response.getheader('Server'))

內容

import urllib.request

response = urllib.request.urlopen('https://www.python.org')
print(response.read().decode('utf-8'))

3、request

import urllib.request

request = urllib.request.Request('https://python.org')
response = urllib.request.urlopen(request)
print(response.read().decode('utf-8'))

設置參數

from urllib import request, parse

url = 'http://httpbin.org/post'
headers = {
    'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
    'Host': 'httpbin.org'
}
dict = {
    'name': 'Germey'
}
data = bytes(parse.urlencode(dict), encoding='utf8')
req = request.Request(url=url, data=data, headers=headers, method='POST')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

add_header()

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')
req.add_header('User-Agent', 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

3、Hander

代理

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())

cookie打印

import http.cookiejar, urllib.request

cookie = http.cookiejar.CookieJar()
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
for item in cookie:
    print(item.name+"="+item.value)

cookie保存 - 火狐

import http.cookiejar, urllib.request
filename = "cookie.txt"
cookie = http.cookiejar.MozillaCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True, ignore_expires=True)

cookie保存 - LWP

import http.cookiejar, urllib.request
filename = 'cookie.txt'
cookie = http.cookiejar.LWPCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True, ignore_expires=True

cookie讀取

import http.cookiejar, urllib.request
cookie = http.cookiejar.LWPCookieJar()
cookie.load('cookie.txt', ignore_discard=True, ignore_expires=True)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
print(response.read().decode('utf-8'))

4、異常處理

捕捉打印異常

from urllib import request, error
try:
    response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.URLError as e:
    print(e.reason)

打印詳細信息

from urllib import request, error

try:
    response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.HTTPError as e:
    print(e.reason, e.code, e.headers, sep='\n')
except error.URLError as e:
    print(e.reason)
else:
    print('Request Successfully')

驗證異常

import socket
import urllib.request
import urllib.error

try:
    response = urllib.request.urlopen('https://www.baidu.com', timeout=0.01)
except urllib.error.URLError as e:
    print(type(e.reason))
    if isinstance(e.reason, socket.timeout):
        print('TIME OUT')

5、URL解析

urlparse

urllib.parse.urlparse(urlstring, scheme='', allow_fragments=True)

from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index.html;user?id=5#comment')
print(type(result), result)

from urllib.parse import urlparse

result = urlparse('www.baidu.com/index.html;user?id=5#comment', scheme='https')
print(result)

from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', allow_fragments=False)
print(result)

urlunparse拼接

from urllib.parse import urlunparse

data = ['http', 'www.baidu.com', 'index.html', 'user', 'a=6', 'comment']
print(urlunparse(data))

urljoin合併

from urllib.parse import urljoin

print(urljoin('http://www.baidu.com', 'FAQ.html'))
print(urljoin('http://www.baidu.com', 'https://cuiqingcai.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://cuiqingcai.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://cuiqingcai.com/FAQ.html?question=2'))
print(urljoin('http://www.baidu.com?wd=abc', 'https://cuiqingcai.com/index.php'))
print(urljoin('http://www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com#comment', '?category=2'))

urlencode字典轉請求參數

from urllib.parse import urlencode

params = {
    'name': 'germey',
    'age': 22
}
base_url = 'http://www.baidu.com?'
url = base_url + urlencode(params)
print(url)

6、robotparser

import urllib.robotparser
rp = urllib.robotparser.RobotFileParser()
rp.set_url("http://www.musi-cal.com/robots.txt")
rp.read()
rrate = rp.request_rate("*")
print(rrate.requests)
print(rrate.seconds)
print(rp.crawl_delay("*"))
print(rp.can_fetch("*", "http://www.musi-cal.com/cgi-bin/search?city=San+Francisco"))
print(rp.can_fetch("*", "http://www.musi-cal.com/"))