urllib.request
urllib當中使用最多的模塊,涉及請求,響應,瀏覽器模擬,代理,cookie等功能。
request.urlopen(url, data=None, timeout=10) #url: 需要打開的網址 #data:Post提交的數據 #timeout:設置網站的訪問超時時間 from urllib import request import ssl # 解決某些環境下報<urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed ssl._create_default_https_context = ssl._create_unverified_context url = 'https://www.jianshu.com' #返回<http.client.HTTPResponse object at 0x0000000002E34550> response = request.urlopen(url, data=None, timeout=10) #直接用urllib.request模塊的urlopen()獲取頁面,page的數據格式為bytes類型,需要decode()解碼,轉換成str類型。 page = response.read().decode('utf-8')
需要添加headers頭信息,urlopen不支持,需要使用Request
PC
import urllib.request url = 'https://www.jianshu.com' # 增加header headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.96 Safari/537.36' } request = urllib.request.Request(url,headers=headers) response = urllib.request.urlopen(request) #在urllib里面 判斷是get請求還是post請求,就是判斷是否提交了data參數 print(request.get_method()) >> 輸出結果 GET
req = request.Request('http://www.douban.com/') req.add_header('User-Agent', 'Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) ' 'AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25') with request.urlopen(req) as f: print('Status:', f.status, f.reason) for k, v in f.getheaders(): print('%s: %s' % (k, v)) print('Data:', f.read().decode('utf-8'))
客戶端用於記錄用戶身份,維持登錄信息
import http.cookiejar, urllib.request # 1 創建CookieJar對象 cookie = http.cookiejar.CookieJar() # 使用HTTPCookieProcessor創建cookie處理器, handler = urllib.request.HTTPCookieProcessor(cookie) # 構建opener對象 opener = urllib.request.build_opener(handler) # 將opener安裝為全局 urllib.request.install_opener(opener) data = urllib.request.urlopen(url) # 2 保存cookie為文本 import http.cookiejar, urllib.request filename = "cookie.txt" # 保存類型有很多種 ## 類型1 cookie = http.cookiejar.MozillaCookieJar(filename) ## 類型2 cookie = http.cookiejar.LWPCookieJar(filename) # 使用相應的方法讀取 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) ……
4.設置代理
當需要抓取的網站設置了訪問限制,這時就需要用到代理來抓取數據。
import urllib.request url = 'http://httpbin.org/ip' proxy = {'http':'39.134.108.89:8080','https':'39.134.108.89:8080'} proxies = urllib.request.ProxyHandler(proxy) # 創建代理處理器 opener = urllib.request.build_opener(proxies,urllib.request.HTTPHandler) # 創建特定的opener對象 urllib.request.install_opener(opener) # 安裝全局的opener 把urlopen也變成特定的opener data = urllib.request.urlopen(url) print(data.read().decode())
import urllib.error import urllib.request requset = urllib.request.Request('http://www.usahfkjashfj.com/') try: urllib.request.urlopen(requset).read() except urllib.error.URLError as e: print(e.reason) else: print('success') >> print結果 [Errno 11004] getaddrinfo failed
HTTPError是URLError的子類,在你利用URLopen方法發出一個請求時,服務器上都會對應一個應答對象response,其中他包含一個數字“狀態碼”,
例如response是一個重定向,需定位到別的地址獲取文檔,urllib將對此進行處理。其他不能處理的,URLopen會產生一個HTTPError,對應相應的狀態碼,
HTTP狀態碼表示HTTP協議所返回的響應的狀態。
from urllib import request, error try: response = request.urlopen('http://cuiqingcai.com/index.htm') except error.URLError as e: print(e.reason) # 先捕獲子類錯誤 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')
>> print結果
Not Found
-------------
Not Found
404
Server: nginx/1.10.3 (Ubuntu)
Date: Thu, 08 Feb 2018 14:45:39 GMT
Content-Type: text/html; charset=UTF-8
Transfer-Encoding: chunked
Connection: close
Vary: Cookie
Expires: Wed, 11 Jan 1984 05:00:00 GMT
print(parse.urljoin('https://www.jianshu.com/xyz','FAQ.html')) print(parse.urljoin('http://www.baidu.com/about.html','http://www.baidu.com/FAQ.html')) >>結果 https://www.jianshu.com/FAQ.html http://www.baidu.com/FAQ.html
urllib.parse.urlencode 字典轉字符串
from urllib import request, parse url = r'https://www.jianshu.com/collections/20f7f4031550/mark_viewed.json' headers = { 'User-Agent': r'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36', 'Referer': r'https://www.jianshu.com/c/20f7f4031550?utm_medium=index-collections&utm_source=desktop', 'Connection': 'keep-alive' } data = { 'uuid': '5a9a30b5-3259-4fa0-ab1f-be647dbeb08a', } #Post的數據必須是bytes或者iterable of bytes,不能是str,因此需要進行encode()編碼 data = parse.urlencode(data).encode('utf-8') print(data) req = request.Request(url, headers=headers, data=data) page = request.urlopen(req).read() page = page.decode('utf-8') print(page) >>結果 b'uuid=5a9a30b5-3259-4fa0-ab1f-be647dbeb08a' {"message":"success"}
urllib.parse.quote url編碼
urllib.parse.unquote url解碼
Url的編碼格式采用的是ASCII碼,而不是Unicode,比如
http://so.biquge.la/cse/search?s=7138806708853866527&q=%CD%EA%C3%C0%CA%C0%BD%E7
from urllib import parse x = parse.quote('山西', encoding='gb18030')# encoding='GBK print(x) #%C9%BD%CE%F7 city = parse.unquote('%E5%B1%B1%E8%A5%BF',) # encoding='utf-8' print(city) # 山西
urllib3包
Urllib3是一個功能強大,條理清晰,用於HTTP客戶端的Python庫,許多Python的原生系統已經開始使用urllib3。Urllib3提供了很多python標准庫里所沒有的重要特性:
1.線程安全
2.連接池
3.客戶端SSL/TLS驗證
4.文件分部編碼上傳
5.協助處理重復請求和HTTP重定位
6.支持壓縮編碼
7.支持HTTP和SOCKS代理
安裝:
Urllib3 能通過pip來安裝:
$pip install urllib3
你也可以在github上下載最新的源碼,解壓之后進行安裝:
$git clone git://github.com/shazow/urllib3.git
$python setup.py install
urllib3的使用:
request GET請求
import urllib3 import requests # 忽略警告:InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. requests.packages.urllib3.disable_warnings() # 一個PoolManager實例來生成請求, 由該實例對象處理與線程池的連接以及線程安全的所有細節 http = urllib3.PoolManager() # 通過request()方法創建一個請求: r = http.request('GET', 'http://cuiqingcai.com/') print(r.status) # 200 # 獲得html源碼,utf-8解碼 print(r.data.decode())
request GET請求(添加數據)
header = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36' } r = http.request('GET', 'https://www.baidu.com/s?', fields={'wd': 'hello'}, headers=header) print(r.status) # 200 print(r.data.decode())
post請求
#你還可以通過request()方法向請求(request)中添加一些其他信息,如: header = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36' } r = http.request('POST', 'http://httpbin.org/post', fields={'hello':'world'}, headers=header) print(r.data.decode())
# 對於POST和PUT請求(request),需要手動對傳入數據進行編碼,然后加在URL之后: encode_arg = urllib.parse.urlencode({'arg': '我的'}) print(encode_arg.encode()) r = http.request('POST', 'http://httpbin.org/post?'+encode_arg, headers=header) # unicode解碼 print(r.data.decode('unicode_escape'))
發送json數據
#JSON:在發起請求時,可以通過定義body 參數並定義headers的Content-Type參數來發送一個已經過編譯的JSON數據: import json data={'attribute':'value'} encode_data= json.dumps(data).encode() r = http.request('POST', 'http://httpbin.org/post', body=encode_data, headers={'Content-Type':'application/json'} ) print(r.data.decode('unicode_escape'))
上傳文件
#使用multipart/form-data編碼方式上傳文件,可以使用和傳入Form data數據一樣的方法進行,並將文件定義為一個元組的形式 (file_name,file_data): with open('1.txt','r+',encoding='UTF-8') as f: file_read = f.read() r = http.request('POST', 'http://httpbin.org/post', fields={'filefield':('1.txt', file_read, 'text/plain') }) print(r.data.decode('unicode_escape')) #二進制文件 with open('websocket.jpg','rb') as f2: binary_read = f2.read() r = http.request('POST', 'http://httpbin.org/post', body=binary_read, headers={'Content-Type': 'image/jpeg'}) # # print(json.loads(r.data.decode('utf-8'))['data'] ) print(r.data.decode('utf-8'))
使用Timeout
#使用timeout,可以控制請求的運行時間。在一些簡單的應用中,可以將timeout參數設置為一個浮點數: r = http.request('POST', 'http://httpbin.org/post',timeout=3.0) print(r.data.decode('utf-8')) #讓所有的request都遵循一個timeout,可以將timeout參數定義在PoolManager中: http = urllib3.PoolManager(timeout=3.0)
對重試和重定向進行控制
#通過設置retries參數對重試進行控制。Urllib3默認進行3次請求重試,並進行3次方向改變。 r = http.request('GET', 'http://httpbin.org/ip',retries=5)#請求重試的次數為5 print(r.data.decode('utf-8')) ##關閉請求重試(retrying request)及重定向(redirect)只要將retries定義為False即可: r = http.request('GET', 'http://httpbin.org/redirect/1',retries=False,redirect=False) print('d1',r.data.decode('utf-8')) #關閉重定向(redirect)但保持重試(retrying request),將redirect參數定義為False即可 r = http.request('GET', 'http://httpbin.org/redirect/1',redirect=False)