1. 程式人生 > >python 爬蟲 訪問網頁之request與requests:

python 爬蟲 訪問網頁之request與requests:

標籤(空格分隔): 9.23

一、訪問獲取網頁的基本方法:

準備頭部和代理

user_agent = [   #準備頭部,列表
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
    "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
    "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
    "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
    "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
    "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
    "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
    "Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
    "UCWEB7.0.2.37/28/999",
    "NOKIA5700/ UCWEB7.0.2.37/28/999",
    "Openwave/ UCWEB7.0.2.37/28/999",
    "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
    # iPhone 6:
    "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",
]

#代理一般去西刺獲取
proxies = [
    '61.135.217.7:80',
    '118.190.95.35:9001'
    '118.190.210.227:3128',
    '118.190.199.55:80'
]

ips = [
{'HTTPS':'140.207.50.246:51426','HTTP':'116.1.11.19:80'},
{'HTTPS':'106.75.226.36:808','HTTP':'118.178.227.171:80'},
{'HTTPS':'123.207.30.131:80','HTTP':'118.190.95.43:9001'},
{'HTTPS':'60.12.89.218:57299','HTTP':'61.135.217.7:80'},
{'HTTPS':'124.235.135.74:80','HTTP':'106.75.225.83:808'},
{'HTTPS':'59.45.16.10:59156','HTTP':'118.190.95.35:9001'},
{'HTTPS':'222.242.155.69:40919','HTTP':'218.23.124.52:59361'},
{'HTTPS':'220.172.40.190:80','HTTP':'124.234.157.228:80'},
{'HTTPS':'60.211.192.54:40700','HTTP':'58.51.83.102:808'},
{'HTTPS':'122.227.182.102:33174','HTTP':'110.73.42.11:8123'},
{'HTTPS':'219.139.35.70:42993','HTTP':'110.73.10.32:8123'},
{'HTTPS':'222.76.204.110:808','HTTP':'182.88.135.132:8123'},
]

1.使用urllib模組中的request

from urllib import request
url = 'http://www.baidu.com'
myrequest = request.Request(url)   #請求
result = request.urlopen(myrequest)  #結果
myresult = result.read()        #讀取
print(myresult)

獲取編碼格式,解碼

import chardet
code = chardet.detect(myresult)['encoding']   #獲取編碼格式(讀取字典)
#print(code)  #匹配requests 模組使用
html = myresult.decode(code)   #解碼
print(html)

簡單設定頭部和代理(固定寫法,不建議使用)

import random
import urllib
from urllib import request
url = "http://www.baidu.com"
#包裝請求
myrequest = request.Request(url)
# user_agent 在最上面
myrequest.add_header("User-Agent",random.choice(user_agent))
# proxies 在最上面
proxy_support = urllib.request.ProxyHandler({"http:":random.choice(proxies)})
opener = request.build_opener(proxy_support)
request.install_opener(opener)  #把代理IP裝進去
#訪問結果
result=request.urlopen(myrequest)
#得到結果
html = result.read().decode("utf-8")
print(html)

2.使用requests訪問網頁(簡單易用)

import requests
import chardet
import random
url = 'https://www.baidu.com'

response = requests.get(
    url,
    headers={'User-Agent':random.choice(user_agent)},
    proxies = random.choice(ips)
    )
#print(response.text)  #列印成文字格式
#獲取編碼
code = chardet.detect(response.content)['encoding']
#解碼
response.encoding = code
print(response.text)#列印資訊