{"id":1552,"date":"2023-03-25T11:26:10","date_gmt":"2023-03-25T03:26:10","guid":{"rendered":""},"modified":"2023-03-25T11:26:10","modified_gmt":"2023-03-25T03:26:10","slug":"Python Urllib\u5e93","status":"publish","type":"post","link":"https:\/\/bianchenghao6.com\/1552.html","title":{"rendered":"Python Urllib\u5e93"},"content":{"rendered":"
\n
Python Urllib\u5e93\u8be6\u7ec6\u6559\u7a0b<\/span>\n <\/div>\n url\uff1a<\/b> \u7f51\u9875\u5730\u5740\uff0c\u6253\u5f00url\u53ef\u4ee5\u662f\u5b57\u7b26\u4e32\u6216\u8005\u662fRequest\u5bf9\u8c61\u3002<\/span> geturl():<\/b> \u8fd4\u56de\u68c0\u7d22\u7684\u8d44\u6e90\u7684URL\uff0c\u901a\u5e38\u7528\u4e8e\u786e\u5b9a\u662f\u5426\u9075\u5faa\u91cd\u5b9a\u5411;<\/span> urllib<\/h2>\n
import <\/span>urllib.request
# \u7f51\u7ad9\u662fhttps\u8bbf\u95ee\u7684\u9700\u8981\u5f15\u5165ssl\u6a21\u5757<\/span>
import <\/span>ssl
# \u5bfc\u5165ssl\u65f6\u5173\u95ed\u8bc1\u4e66\u9a8c\u8bc1<\/span>
ssl._create_default_https_context = ssl._create_unverified_context
response = urllib.request.urlopen<\/span>('https:\/\/www.lidihuo.com\/python\/spider-test.html'<\/span>)
print(response.read<\/span>().decode<\/span>('utf-8'<\/span>))
<\/span><\/code><\/pre>\n<\/p><\/div>\n <html lang=\"en\">
<head>
<meta charset=\"UTF-8\">
<title>python spider <\/title>
<\/head>
<body>
Hello\uff0cI am lidihuo
Welcome to Python spider
<\/body>
<\/html> <\/span><\/code><\/pre>\n<\/p><\/div>\n import <\/span>urllib.request
# \u7f51\u7ad9\u662fhttps\u8bbf\u95ee\u7684\u9700\u8981\u5f15\u5165ssl\u6a21\u5757<\/span>
import <\/span>ssl
# \u5bfc\u5165ssl\u65f6\u5173\u95ed\u8bc1\u4e66\u9a8c\u8bc1<\/span>
ssl._create_default_https_context = ssl._create_unverified_context
url = 'https:\/\/www.lidihuo.com\/python\/spider-test.html'<\/span>
url = url + '?'<\/span> + key + '='<\/span><\/span> + value1 + '&'<\/span> + key2 + '=' + value2
response = urllib.request.urlopen<\/span>(url)
# print(response.read().decode('utf-8'))<\/span> <\/span><\/code><\/pre>\n<\/p><\/div>\nurllib.request.urlopen(url, data=None, [timeout, ]*, cafile=None, capath=None, cadefault=False, context=None)<\/code><\/pre>\n<\/p><\/div>\n
\u53c2\u6570\u8bf4\u660e\uff1a<\/h3>\n
\n data\uff1a<\/b> \u4e00\u4e2a\u5b9a\u4e49\u4e86\u5411\u670d\u52a1\u5668\u6240\u53d1\u9001\u989d\u5916\u6570\u636e\u7684\u5bf9\u8c61\uff0c\u6216\u8005\u5982\u679c\u6ca1\u6709\u5fc5\u8981\u6570\u636e\u7684\u8bdd\uff0c\u5c31\u662fNone\u503c\u3002<\/span>
\n timeout:<\/b> \u53c2\u6570\u6307\u5b9a\u963b\u6b62\u8bf8\u5982\u8fde\u63a5\u5c1d\u8bd5\u7b49\u64cd\u4f5c\u7684\u8d85\u65f6\u65f6\u95f4\uff08\u4ee5\u79d2\u4e3a\u5355\u4f4d\uff09<\/span>
\n context:<\/b> \u63cf\u8ff0\u5404\u79cdSSL\u9009\u9879\u7684ssl.SSLContext\u5b9e\u4f8b\u3002 <\/span>
\n cafile\/capath:<\/b> \u4e3aHTTPS\u8bf7\u6c42\u6307\u5b9a\u4e00\u7ec4\u53ef\u4fe1\u7684CA\u8bc1\u4e66\u3002<\/span> <\/p>\n\u8fd4\u56de\u503c\uff1a<\/h3>\n
\n info():<\/b> \u4ee5email.message_from_string\uff08\uff09\u5b9e\u4f8b\u7684\u5f62\u5f0f\u8fd4\u56de\u9875\u9762\u7684\u5143\u4fe1\u606f\uff08\u5982headers\uff09\uff08\u53ef\u5feb\u901f\u53c2\u8003HTTP Headers\uff09;<\/span>
\n getcode():<\/b> \u8fd4\u56de\u54cd\u5e94\u7684HTTP\u72b6\u6001\u7801\u3002<\/span> <\/p>\n
\n
\u9664\u4e0a\u8ff0\u4e09\u79cd\u65b0\u65b9\u6cd5\u4e4b\u5916\uff0cmsg\u5c5e\u6027\u8fd8\u5305\u542b\u4e0ereason\u5c5e\u6027\uff08\u670d\u52a1\u5668\u8fd4\u56de\u7684\u539f\u56e0\u77ed\u8bed\uff09\u76f8\u540c\u7684\u4fe1\u606f\uff0c\u800c\u4e0d\u662fHTTPResponse\u6587\u6863\u4e2d\u6307\u5b9a\u7684\u54cd\u5e94\u6807\u5934\u3002
\n
\u5bf9\u4e8e\u7531\u4f20\u7edfURLopener\u548cFancyURLopener\u7c7b\u660e\u786e\u5904\u7406\u7684FTP\uff0c\u6587\u4ef6\u548c\u6570\u636eURL\u548c\u8bf7\u6c42\uff0c\u6b64\u51fd\u6570\u8fd4\u56de\u4e00\u4e2aurllib.response.addinfourl\u5bf9\u8c61\u3002
\n
\u5728\u534f\u8bae\u9519\u8bef\u4e0a\u5f15\u53d1URLError\u3002
\n
\u8bf7\u6ce8\u610f\uff0c\u5982\u679c\u6ca1\u6709\u5904\u7406\u8bf7\u6c42\u7684handler\uff0c\u5219\u53ef\u80fd\u8fd4\u56deNone\uff08\u5c3d\u7ba1\u9ed8\u8ba4\u5b89\u88c5\u7684\u5168\u5c40OpenerDirector\u4f7f\u7528UnknownHandler\u6765\u786e\u4fdd\u6c38\u4e0d\u53d1\u751f\u8fd9\u79cd\u60c5\u51b5\uff09\u3002
\n
\u53e6\u5916\uff0c\u5982\u679c\u68c0\u6d4b\u5230\u4ee3\u7406\u8bbe\u7f6e\uff08\u4f8b\u5982\uff0c\u5982\u679c\u8bbe\u7f6e\u4e86\u8bf8\u5982http_proxy\u7684* _proxy\u73af\u5883\u53d8\u91cf\uff09\uff0c\u5219\u9ed8\u8ba4\u5b89\u88c5ProxyHandler\uff0c\u5e76\u786e\u4fdd\u901a\u8fc7\u4ee3\u7406\u5904\u7406\u8bf7\u6c42\u3002
\n
\u6765\u81eaPython 2.6\u53ca\u66f4\u65e9\u7248\u672c\u7684\u9057\u7559urllib.urlopen\u51fd\u6570\u5df2\u505c\u6b62\u4f7f\u7528; urllib.request.urlopen\uff08\uff09\u5bf9\u5e94\u4e8e\u65e7\u7684urllib2.urlopen\u3002
\n
\u901a\u8fc7\u4f7f\u7528ProxyHandler\u5bf9\u8c61\u53ef\u4ee5\u83b7\u5f97\u901a\u8fc7\u5c06\u5b57\u5178\u53c2\u6570\u4f20\u9012\u7ed9urllib.urlopen\u5b8c\u6210\u7684\u4ee3\u7406\u5904\u7406\u3002\n <\/div>\nPOST\/GET\u8bf7\u6c42<\/h2>\n
POST\u65b9\u5f0f\uff1a<\/h3>\n
# Filename : example.py<\/span>
# Copyright : 2020 By Lidihuo<\/span>
# Author by : www.lidihuo.com<\/span>
# Date : 2020-08-19<\/span>
#post \u8bf7\u6c42
<\/span> import <\/span>urllib.request
import <\/span>urllib.parse
base_url=\"\u4f60\u7684\u8bf7\u6c42\u7f51\u5740\"<\/span>
# \u4f60\u8bf7\u6c42\u7f51\u5740\u7684\u53c2\u6570
<\/span> data={
\"name\"<\/span>:\"www.lidihuo.com\"<\/span>,
\"pass\"<\/span>:\"xxxx\"<\/span>
}
headers={\"User-Agent\"<\/span>:\"Mozilla\/5.0 <\/span>(Windows NT 6.1; WOW64) AppleWebKit\/537.36 <\/span>(KHTML, like Gecko) Chrome\/63.0.3239.132 Safari\/537.36 QIHU 360SE\"<\/span>}
postdata=urllib.parse.urlencode<\/span>(data).encode<\/span>('utf-8'<\/span><\/span>)
req=urllib.request.Request<\/span>(url=base_url,headers=headers,data=postdata,method='POST'<\/span>)
response=urllib.request.urlopen<\/span>(req)
html=response.read<\/span>()
# html=response.read<\/span>().decode<\/span>('utf-8') #\u8fd9\u91cc\u8bb2\u89e3\u4e00\u4e0bdecode()\u662f\u628abytes\u8f6c\u5316\u89e3\u7801\u4e3a\u4e86 str ,
<\/span> print(html)
<\/span><\/code><\/pre>\n<\/p><\/div>\nGET\u65b9\u5f0f\u8bf7\u6c42\uff1a<\/h3>\n
# Filename : example.py<\/span>
# Copyright : 2020 By Lidihuo<\/span>
# Author by : www.lidihuo.com<\/span>
# Date : 2020-08-19<\/span>
from <\/span>urllib import <\/span>parse, request
import <\/span>random
url = 'https:\/\/www.lidihuo.com\/python\/spider-test.html'<\/span>
keyvalue = 'url\u53c2\u6570'<\/span>
encoded_wd = parse.urlencode<\/span>(wd)
new_url = url + '?'<\/span> + encoded_wd
req = request.Request<\/span>(url)
# \u4e3a\u4e86\u9632\u6b62\u88ab\u7f51\u7ad9\u5c01ip\uff0c\u6a21\u4eff\u6d4f\u89c8\u5668\u8bbf\u95ee\u7f51\u7ad9
<\/span> ua_list = [
\"Mozilla\/5.0 <\/span>(Macintosh; Intel Mac OS X 10.6; rv2.0.1) Gecko\/20100101 Firefox\/4.0.1\"<\/span>,
\"Mozilla\/5.0 <\/span>(Windows NT 6.1; rv2.0.1) Gecko\/20100101 Firefox\/4.0.1\"<\/span>,
\"Opera\/9.80 <\/span>(Macintosh; Intel Mac OS X 10.6.8; U; en) Presto\/2.8.131 Version\/11.11\"<\/span>,
\"Opera\/9.80 <\/span>(Windows NT 6.1; U; en) Presto\/2.8.131 Version\/11.11\"<\/span>,
\"Mozilla\/5.0 <\/span>(Macintosh; Intel Mac OS X 10_7_0) AppleWebKit\/535.11 <\/span>(KHTML, like Gecko) Chrome\/17.0.963.56 Safari\/535.11\"<\/span>
]
# \u5728User-Agent\u5217\u8868\u91cc\u968f\u673a\u9009\u62e9\u4e00\u4e2aUser-Agent ;\u4ece\u5e8f\u5217\u4e2d\u968f\u673a\u9009\u53d6\u4e00\u4e2a\u5143\u7d20
<\/span> user_agent = random.choice<\/span>(ua_list)
req.add_header<\/span>('User-Agent'<\/span>, user_agent)
response = request.urlopen<\/span>(req)
print(response.read<\/span>().decode<\/span>('utf-8'<\/span>))
<\/span><\/code><\/pre>\n<\/p><\/div>\nPUT\/DELETE\u8bf7\u6c42<\/h2>\n
\n
PUT\u548cPOST\u6781\u4e3a\u76f8\u4f3c\uff0c\u90fd\u662f\u5411\u670d\u52a1\u5668\u53d1\u9001\u6570\u636e\uff0c\u4f46\u5b83\u4eec\u4e4b\u95f4\u6709\u4e00\u4e2a\u91cd\u8981\u533a\u522b\uff0cPUT\u901a\u5e38\u6307\u5b9a\u4e86\u8d44\u6e90\u7684\u5b58\u653e\u4f4d\u7f6e\uff0c\u800cPOST\u5219\u6ca1\u6709\uff0cPOST\u7684\u6570\u636e\u5b58\u653e\u4f4d\u7f6e\u7531\u670d\u52a1\u5668\u81ea\u5df1\u51b3\u5b9a\u3002
\n
DELETE\uff1a\u5220\u9664\u67d0\u4e00\u4e2a\u8d44\u6e90\u3002\u57fa\u672c\u4e0a\u8fd9\u4e2a\u4e5f\u5f88\u5c11\u89c1\uff0c\u4e0d\u8fc7\u8fd8\u662f\u6709\u4e00\u4e9b\u5730\u65b9\u6bd4\u5982amazon\u7684S3\u4e91\u670d\u52a1\u91cc\u9762\u5c31\u7528\u7684\u8fd9\u4e2a\u65b9\u6cd5\u6765\u5220\u9664\u8d44\u6e90\u3002\n <\/div>\n # Filename : example.py<\/span>
# Copyright : 2020 By Lidihuo<\/span>
# Author by : www.lidihuo.com<\/span>
# Date : 2020-08-20<\/span>
import <\/span>urllib.request
DATA=b'some data'<\/span>
req = urllib.request.Request<\/span>(url='\u7f51\u5740'<\/span>, data='\u53c2\u6570'<\/span>,method='PUT\/DELETE'<\/span>)
f = urllib.request.urlopen<\/span>(req)
print(f.status)
print(f.reason)
<\/span><\/code><\/pre>\n<\/p><\/div>\n\u8bbe\u7f6eHeaders<\/h2>\n
\n User-Agent : \u6709\u4e9b\u670d\u52a1\u5668\u6216 Proxy \u4f1a\u901a\u8fc7\u8be5\u503c\u6765\u5224\u65ad\u662f\u5426\u662f\u6d4f\u89c8\u5668\u53d1\u51fa\u7684\u8bf7\u6c42\u3002<\/span>
\n Content-Type : \u5728\u4f7f\u7528 REST \u63a5\u53e3\u65f6\uff0c\u670d\u52a1\u5668\u4f1a\u68c0\u67e5\u8be5\u503c\uff0c\u7528\u6765\u786e\u5b9a HTTP Body \u4e2d\u7684\u5185\u5bb9\u8be5\u600e\u6837\u89e3\u6790\u3002<\/span>
\n application\/xml \uff1a \u5728 XML RPC\uff0c\u5982 RESTful\/SOAP \u8c03\u7528\u65f6\u4f7f\u7528\u3002<\/span>
\n application\/json \uff1a \u5728 JSON RPC \u8c03\u7528\u65f6\u4f7f\u7528\u3002<\/span>
\n application\/x-www-form-urlencoded \uff1a \u6d4f\u89c8\u5668\u63d0\u4ea4 Web \u8868\u5355\u65f6\u4f7f\u7528\u3002<\/span> <\/p>\n # Filename : example.py<\/span>
# Copyright : 2020 By Lidihuo<\/span>
# Author by : www.lidihuo.com<\/span>
# Date : 2020-08-20<\/span>
# \u4f2a\u88c5\u6d4f\u89c8\u5668\u7684\u722c\u866b
<\/span> from <\/span>urllib import <\/span>request
import <\/span>re
import <\/span>ssl
url=\"https:\/\/www.lidihuo.com\/python\/spider-test.html\"<\/span>
# \u5bfc\u5165ssl\u65f6\u5173\u95ed\u8bc1\u4e66\u9a8c\u8bc1
<\/span> ssl._create_default_https_context = ssl._create_unverified_context
# \u6784\u9020\u8bf7\u6c42\u5934\u4fe1\u606f
<\/span> header={
'User-Agent'<\/span>:'Mozilla\/5.0 <\/span>(Windows NT 6.1; WOW64) AppleWebKit\/537.36 <\/span>(KHTML, like Gecko) Chrome\/63.0.3239.132 Safari\/537.36'<\/span>
}
req=request.Request<\/span>(url,headers=header)
# \u53d1\u9001\u8bf7\u6c42.\u83b7\u53d6\u54cd\u5e94\u4fe1\u606f
<\/span> reponse=request.urlopen<\/span>(req).read<\/span>().decode<\/span>() #\u89e3\u7801---\uff08\u7f16\u7801encode()\uff09
<\/span> pat=r\"
data=re.findall<\/span>(pat,reponse)
#\u7531\u4e8edata\u8fd4\u56de\u7684\u662f\u5217\u8868\u5f62\u5f0f\u7684\u6570\u636e\u7528data[0]\u76f4\u63a5\u53d6\u503c
<\/span> print(data[0])
<\/span><\/code><\/pre>\n<\/p><\/div>\npython spider \n
<\/code><\/pre>\n<\/p><\/div>\nProxy\uff08\u4ee3\u7406\uff09\u7684\u8bbe\u7f6e<\/h2>\n
# Filename : example.py<\/span>
# Copyright : 2020 By Lidihuo<\/span>
# Author by : www.lidihuo.com<\/span>
# Date : 2020-08-20<\/span>
def <\/span>load_page(url, form_data):
USER_AGENTS = [
\"Mozilla\/5.0 <\/span>(compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident\/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)\"<\/span>,
\"Mozilla\/5.0 <\/span>(compatible; MSIE 8.0; Windows NT 6.0; Trident\/4.0; WOW64; Trident\/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)\"<\/span>,
\"Mozilla\/4.0 <\/span>(compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)\"<\/span>,
\"Mozilla\/5.0 <\/span>(Windows; U; Windows NT 5.1; zh-CN) AppleWebKit\/523.15 <\/span>(KHTML, like Gecko, Safari\/419.3) Arora\/0.3 <\/span>(Change: 287 c9dfb30)\"<\/span>,
\"Mozilla\/5.0 <\/span>(X11; U; Linux; en-US) AppleWebKit\/527+ (KHTML, like Gecko, Safari\/419.3) Arora\/0.6\"<\/span>,
\"Mozilla\/5.0 <\/span>(Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko\/20070215 K-Ninja\/2.1.1\"<\/span>,
\"Mozilla\/5.0 <\/span>(Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko\/20080705 Firefox\/3.0 Kapiko\/3.0\"<\/span>,
\"Mozilla\/5.0 <\/span>(X11; Linux i686; U;) Gecko\/20070322 Kazehakase\/0.4.5\"<\/span>
]
user_agent = random.choice<\/span>(USER_AGENTS)
headers = {
'User-Agent'<\/span>:user_agent
}
<\/span><\/code><\/pre>\n<\/p><\/div>\n # Filename : example.py<\/span>
# Copyright : 2020 By Lidihuo<\/span>
# Author by : www.lidihuo.com<\/span>
# Date : 2020-08-20<\/span>
from <\/span>urllib.error import <\/span>URLError
from <\/span>urllib.request import <\/span>ProxyHandler, build_opener
proxy = '127.0.0.1:8088'<\/span>
# \u53c2\u6570\u662f\u5b57\u5178\uff0c\u952e\u540d\u662f\u534f\u8bae\u7c7b\u578b\uff0c\u5065\u503c\u662f\u4ee3\u7406
<\/span> proxy_handler = ProxyHandler({
'http'<\/span>: 'http:\/\/'<\/span> + proxy,
'https'<\/span>: 'https:\/\/'<\/span> + proxy
})
# Opener\u5df2\u7ecf\u8bbe\u7f6e\u597d\u4ee3\u7406\u4e86
<\/span> opener = build_opener(proxy_handler)
try:
response = opener.open<\/span>('https:\/\/www.lidihuo.com\/python\/spider-test.html'<\/span>)
# \u8fd0\u884c\u7ed3\u679c\u662f\u4e00\u4e2aJSON
<\/span> print(response.read<\/span>().