Python网络爬虫（requests, 代理，Web认证, SSL证书认证）

requests模块

    代理（proxies）

        西刺代理

        快代理

        全网代理

        高匿ip：看不到真实ip

        透明ip：可以看到代理 和 真实ip

    普通代理

        proxies = {"协议":"协议://IP地址:端口号"}

'''01_普通代理示例.py'''
import requests

url = "http://www.baidu.com/"
proxies = {"http":"http://183.129.207.82:11597"}
headers = {"User-Agent":"Mozilla/5.0"}

res = requests.get(url,proxies=proxies,headers=headers)
print(res.status_code)

    私密代理

        proxies = {"协议": "协议://用户名:密码@ip地址:端口号"}

'''02_私密代理示例.py'''
import requests

url = "http://httpbin.org/get"
headers = {"User-Agent":"Mozilla/5.0"}
proxies = {"http":"http://309435365:[email protected]:16817"}

res = requests.get(url,proxies=proxies,headers=headers)
res.encoding = "utf-8"
print(res.text)

爬取链家二手房信息 --> 存到MySQL数据库中

'''05_链家数据ToMongo.py'''
import requests
import re
import pymysql
import warnings

class LianjiaSpider:
    def __init__(self):
        self.baseurl = "https://bj.lianjia.com/ershoufang/pg"
        self.page = 1
        self.headers = {"User-Agent": "Mozilla/5.0"}
        self.proxies = {"http": "http://127.0.0.1：8888"}
        self.db = pymysql.connect("localhost",
                  "root","ParisPython",charset="utf8")
        self.cursor = self.db.cursor()

    def getPage(self,url):
        res = requests.get(url,proxies=self.proxies,headers=self.headers,timeout=5)
        res.encoding = "utf-8"
        html = res.text
        print("页面爬取成功,正在解析...")
        self.parsePage(html)

    def parsePage(self,html):
        p = re.compile('<div class="houseInfo".*?data-el="region">(.*?)</a>.*?<div class="totalPrice">.*?<span>(.*?)</span>(.*?)</div>',re.S)
        r_list = p.findall(html)
        # [("天通苑","480","万"),()..]
        print("页面解析完成,正在存入数据库...")
        self.writeTomysql(r_list)

    def writeTomysql(self,r_list):
        c_db = "create database if not exists Lianjiadb \
                character set utf8"
        u_db = "use Lianjiadb"
        c_tab = "create table if not exists housePrice( \
                 id int primary key auto_increment,\
                 housename varchar(50), \
                 totalprice int)charset=utf8"
        
        warnings.filterwarnings("ignore")
        try:
            self.cursor.execute(c_db)
            self.cursor.execute(u_db)
            self.cursor.execute(c_tab)
        except Warning:
            pass

        ins = "insert into housePrice(housename,totalprice) \
               values(%s,%s)"
        for r_tuple in r_list:
            name = r_tuple[0].strip()
            price = float(r_tuple[1].strip())*10000
            L = [name,price]
            self.cursor.execute(ins,L)
            self.db.commit()
        print("存入数据库成功")


    def workOn(self):
        while True:
            c = input("爬取按y(q退出):")
            if c.strip().lower() == "y":
                url = self.baseurl + str(self.page) + "/"
                self.getPage(url)
                self.page += 1
            else:
                self.cursor.close()
                self.db.close()
                print("爬取结束,谢谢使用!")
                break



if __name__ == "__main__":
    spider = LianjiaSpider()
    spider.workOn()

    找URL

      https://bj.lianjia.com/ershoufang/pg1/

    正则

<div class="houseInfo".*?data-el="region">(.*?)</a>.*?<div="totalPrice">.*?<span>(.*?)</span>(.*?)</div>

  Web客户端验证(参数名:auth)

    auth=("用户名","密码")

    案例 ：09_Web客户端验证.py

'''09_Web客户端验证.py'''
import requests
import re

class NoteSpider:
    def __init__(self):
        self.headers = {"User-Agent":"Mozilla/5.0"}
        self.url = "网址"
        self.proxies = {"http":"http://309435365:[email protected]:16817"}
        # auth参数存储用户名和密码(必须为元组)
        self.auth = ("账号","密码")
    
    def getParsePage(self):
        res = requests.get(self.url,
                           proxies=self.proxies,
                           headers=self.headers,
                           auth=self.auth,
                           timeout=3)
        res.encoding = "utf-8"
        html = res.text
        print(html)
        p = re.compile('<a href=".*?>(.*?)</a>',re.S)
        r_list = p.findall(html)
        print(r_list)
        self.writePage(r_list)
        
    def writePage(self,r_list):
        print("开始写入文件...")
        with open("达内科技.txt","a") as f:
            for r_str in r_list:
                f.write(r_str + "\n\n")
        print("写入成功")
    
if __name__ == "__main__":
    spider = NoteSpider()
    spider.getParsePage()

  SSL证书认证(参数名:verify)

    verify = True : 默认,进行SSL证书认证

    verify = False: 不做认证

'''10_SSL证书认证示例.py'''
import requests

url = "https://www.12306.cn/mormhweb/"
headers = {"User-Agent":"Mozilla/5.0"}

res = requests.get(url,headers=headers,verify=False)
res.encoding = "utf-8"
print(res.text)

urllib.request中Handler处理器

  定义

    自定义的urlopen()方法,urlopen()方法是一个特殊的opener(模块已定义好),

    不支持代理等功能,通过Handler处理器对象来自定义opener对象

  常用方法

    build_opener(Handler处理器对象) ：创建opener对象

    opener.open(url,参数)

# 创建Handler处理器对象
http_handler = urllib.request.HTTPHandler()
#proxy_handler = urllib.request.ProxyHandler()
# 创建自定义的opener对象
opener = urllib.request.build_opener(http_handler)
# 利用opener对象的open()方法发请求
req = urllib.request.Request(url)
res = opener.open(req)
print(res.read().decode("utf-8"))

  Handler处理器分类

    HTTPHandler() ：没有任何特殊功能

    ProxyHandler(普通代理)

      代理: {"协议":"IP地址:端口号"}

    ProxyBasicAuthHandler(密码管理器对象) ：私密代理

    HTTPBasicAuthHandler(密码管理器对象) : web客户端认证

    密码管理器对象作用

      私密代理

      Web客户端认证

      程序实现流程

        创建密码管理器对象

  pwdmg = urllib.request.HTTPPasswordMgrWithDefaultRealm()

把认证信息添加到密码管理器对象

  pwdmg.add_password(None,webserver,user,passwd)

创建Handler处理器对象

  私密代理

    proxy = urllib.request.ProxyAuthBasicHandler(pwdmg)

  Web客户端

    webbasic = urllib.request.HTTPBasicAuthHandler(pwdmg)

# 创建Handler处理器对象
pro_hand = urllib.request.ProxyHandler(proxy)
# 创建自定义opener对象
opener = urllib.request.build_opener(pro_hand)
# opener对象open方法发请求
req = urllib.request.Request(url)
res = opener.open(req)
print(res.read().decode("utf-8"))

爬取猫眼电影排行榜存入MongoDB数据库

'''06_猫眼电影top100抓取.py'''
import requests
import re
import pymongo

class MaoyanSpider:
    def __init__(self):
        self.baseurl = "http://maoyan.com/board/4?offset="
        self.headers = {"User-Agent":"Mozilla/5.0"}
        self.page = 1
        self.offset = 0
        self.proxies = {"http":"http://309435365:[email protected]:16817"}
        self.conn = pymongo.MongoClient("localhost",27017)
        self.db = self.conn.Film
        self.myset = self.db.top100

        
    # 下载页面
    def loadPage(self,url):
        res = requests.get(url,headers=self.headers)
        res.encoding = "utf-8"
        html = res.text
        self.parsePage(html)
        
    # 解析页面
    def parsePage(self,html):
        p = re.compile('<div class="movie-item-info">.*?title="(.*?)".*?<p class="star">(.*?)</p>.*?releasetime">(.*?)</p>',re.S)
        r_list = p.findall(html)
#        print(r_list)
        # [("霸王别姬","张国荣","1994-01-01"),(),()...]
        self.writeTomysql(r_list)
    
    def writeTomysql(self,r_list):
        for r_tuple in r_list:
            name = r_tuple[0].strip()
            star = r_tuple[1].strip()
            releasetime = r_tuple[2].strip()
            D = {"name":name,
                 "star":star,
                 "releasetime":releasetime}
            self.myset.insert(D)
        print("存入数据库成功")

    
    def workOn(self):
        while True:
            c = input("爬取请按y(y/n):")
            if c.strip().lower() == "y":
                self.offset = (self.page-1)*10
                url = self.baseurl + str(self.offset)
                self.loadPage(url)
                self.page += 1
            else:
                print("爬取结束,谢谢使用!")
                break

                
if __name__ == "__main__":
    spider = MaoyanSpider()
    spider.workOn()