第三百三十節，web爬蟲講解2—urllib庫爬蟲—實戰爬取搜狗微信公眾號

封裝模塊

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import urllib
from urllib import request
import json
import random
import re
import urllib.error
def hq_html(hq_url):
    """
    hq_html()封裝的爬蟲函數，自動啟用了用戶代理和ip代理
    接收一個參數url,要爬取頁面的url，返回html源碼
    """
    def yh_dl():    #
 
創建用戶代理池
        yhdl = [
            ‘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 (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/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/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; 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‘,
            ‘User-Agent: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‘,
            ‘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 (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‘
            ]
        thisua = random.choice(yhdl)                    #隨機獲取代理信息
        headers = ("User-Agent",thisua)                 #拼接報頭信息
        opener = urllib.request.build_opener()          #創建請求對象
        opener.addheaders=[headers]                     #添加報頭到請求對象
        urllib.request.install_opener(opener)           #將報頭信息設置為全局，urlopen()方法請求時也會自動添加報頭

    def dai_li_ip(hq_url):    #創建ip代理池
        url = "http://http-webapi.zhimaruanjian.com/getip?num=1&type=2&pro=&city=0&yys=0&port=11&time=1&ts=0&ys=0&cs=0&lb=1&sb=0&pb=4&mr=1"
        if url:
            data = urllib.request.urlopen(url).read().decode("utf-8")
            data2 = json.loads(data)  # 將字符串還原它本來的數據類型
            # print(data2[‘data‘][0])
            ip = str(data2[‘data‘][0][‘ip‘])
            dkou = str(data2[‘data‘][0][‘port‘])
            zh_ip = ip + ‘:‘ + dkou
            pat = "(\w*):\w*"
            rst = re.compile(pat).findall(hq_url)  #正則匹配獲取是http協議還是https協議
            rst2 = rst[0]
            proxy = urllib.request.ProxyHandler({rst2: zh_ip})  # 格式化IP,註意，第一個參數，請求目標可能是http或者https,對應設置
            opener = urllib.request.build_opener(proxy, urllib.request.HTTPHandler)  # 初始化IP
            urllib.request.install_opener(opener)  # 將代理IP設置成全局,當使用urlopen()請求時自動使用代理IP
        else:
            pass

    #請求
    try:
        dai_li_ip(hq_url) #執行代理IP函數
        yh_dl()     #執行用戶代理池函數

        data = urllib.request.urlopen(hq_url).read().decode("utf-8")
        return data
    except urllib.error.URLError as e:  # 如果出現錯誤
        if hasattr(e, "code"):  # 如果有錯誤代碼
            # print(e.code)  # 打印錯誤代碼
            pass
        if hasattr(e, "reason"):  # 如果有錯誤信息
            # print(e.reason)  # 打印錯誤信息
            pass

# a = hq_html(‘http://www.baid.com/‘)
# print(a)

實戰爬取搜狗微信公眾號

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import urllib.request
import fzhpach
import re
#抓取搜狗微信公眾號
#http://weixin.sogou.com/weixin?type=1&query=php&page=1
#type=1表示顯示公眾號
#type=2表示抓取文章
#query=關鍵詞
#page=頁碼


gjc = ‘火鍋‘
gjc = urllib.request.quote(gjc)                 #將關鍵詞轉碼成瀏覽器認識的字符，默認網站不能是中文
url = ‘http://weixin.sogou.com/weixin?type=1&query=%s&page=1‘ %(gjc)
html = fzhpach.hq_html(url)                                     #使用我們封裝的爬蟲模塊
pat = ‘微信號：<label name="em_weixinhao">(\w*)</label>‘
rst = re.compile(pat).findall(html)  #正則獲取公眾號
print(rst)

#返回
#[‘cqhuoguo1‘, ‘qkmjscj888‘, ‘cdsbcdhs‘, ‘zk4538111‘, ‘lamanannv‘, ‘ctm2813333‘, ‘cslhg2016‘, ‘gh_978a858b478f‘, ‘CCLWL0431‘, ‘yuhehaixian‘]

第三百三十節，web爬蟲講解2—urllib庫爬蟲—實戰爬取搜狗微信公眾號