python 网络爬虫requests处理cookie,代理IP,云打码介绍

一。基于requests模块的cookie操作（session处理cookie）

    cookie概念：当用户通过浏览器首次访问一个域名时，访问的web服务器会给客户端发送数据，以保持web服务器与客户端之间的状态保持，这些数据就是cookie。

    cookie作用：我们在浏览器中，经常涉及到数据的交换，比如你登录邮箱，登录一个页面。我们经常会在此时设置30天内记住我，或者自动登录选项。那么它们是怎么记录信息的呢，答案就是今天的主角cookie了，Cookie是由HTTP服务器设置的，保存在浏览器中，但HTTP协议是一种无状态协议，在数据交换完毕后，服务器端和客户端的链接就会关闭，每次交换数据都需要建立新的链接。就像我们去超市买东西，没有积分卡的情况下，我们买完东西之后，超市没有我们的任何消费信息，但我们办了积分卡之后，超市就有了我们的消费信息。cookie就像是积分卡，可以保存积分，商品就是我们的信息，超市的系统就像服务器后台，http协议就是交易的过程。

import requests
from lxml import etree
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'
}
#创建一个会话对象:可以像requests模块一样发起请求。如果请求过程中会产生cookie的话，则cookie会被会话自动处理
s = requests.Session()
first_url = 'https://xueqiu.com/'
#请求过程中会产生cookie，cookie就会被存储到session对象中
s.get(url=first_url,headers=headers)


url = 'https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id=-1&count=10&category=-1'
json_obj = s.get(url=url,headers=headers).json()
print(json_obj)

二。打码验证识别验证码实现模拟登陆

云打码使用方法：https://i.cnblogs.com/EditPosts.aspx?postid=10839009&update=1

 获取验证码图片：code_img_src = tree.xpath('//*[@id="verifyPic_login"]/@src')[0]

点击登录会进行页面跳转，Preserve log选项，这个选项是保留跳转与跳转之前所有记录

import http.client, mimetypes, urllib, json, time, requests

######################################################################

class YDMHttp:

    apiurl = 'http://api.yundama.com/api.php'
    username = ''
    password = ''
    appid = ''
    appkey = ''

    def __init__(self, username, password, appid, appkey):
        self.username = username  
        self.password = password
        self.appid = str(appid)
        self.appkey = appkey

    def request(self, fields, files=[]):
        response = self.post_url(self.apiurl, fields, files)
        response = json.loads(response)
        return response
    
    def balance(self):
        data = {'method': 'balance', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['balance']
        else:
            return -9001
    
    def login(self):
        data = {'method': 'login', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['uid']
        else:
            return -9001

    def upload(self, filename, codetype, timeout):
        data = {'method': 'upload', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey, 'codetype': str(codetype), 'timeout': str(timeout)}
        file = {'file': filename}
        response = self.request(data, file)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['cid']
        else:
            return -9001

    def result(self, cid):
        data = {'method': 'result', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey, 'cid': str(cid)}
        response = self.request(data)
        return response and response['text'] or ''

    def decode(self, filename, codetype, timeout):
        cid = self.upload(filename, codetype, timeout)
        if (cid > 0):
            for i in range(0, timeout):
                result = self.result(cid)
                if (result != ''):
                    return cid, result
                else:
                    time.sleep(1)
            return -3003, ''
        else:
            return cid, ''

    def report(self, cid):
        data = {'method': 'report', 'username': self.username, 'password': self.password, 'appid': self.appid, 'appkey': self.appkey, 'cid': str(cid), 'flag': '0'}
        response = self.request(data)
        if (response):
            return response['ret']
        else:
            return -9001

    def post_url(self, url, fields, files=[]):
        for key in files:
            files[key] = open(files[key], 'rb');
        res = requests.post(url, files=files, data=fields)
        return res.text

import requests
from lxml import etree
from YunCode import YDMHttp

#该函数是用来返回验证码图片显示的数据值
def getCodeText(codeType,imgPath):
    result = None
    # 普通者用户名
    username = '用户名'
    
    # 普通者密码
    password = '密码'
    
    # 软件ＩＤ，开发者分成必要参数。登录开发者后台【我的软件】获得！
    appid = id

    # 软件密钥，开发者分成必要参数。登录开发者后台【我的软件】获得！
    appkey = '软件密钥'
    
    # 图片文件
    filename = imgPath
    
    # 验证码类型，# 例：1004表示4位字母数字，不同类型收费不同。请准确填写，否则影响识别率。在此查询所有类型 http://www.yundama.com/price.html
    codetype = codeType
    
    # 超时时间，秒
    timeout = 30
    
    # 检查
    if (username == 'username'):
        print('请设置好相关参数再测试')
    else:
        # 初始化
        yundama = YDMHttp(username, password, appid, appkey)
        
        # 登陆云打码
        uid = yundama.login();
        print('uid: %s' % uid)
        
        # 查询余额
        balance = yundama.balance();
        print('balance: %s' % balance)
        
        # 开始识别，图片路径，验证码类型ID，超时时间（秒），识别结果
        cid, result = yundama.decode(filename, codetype, timeout);
        print('cid: %s, result: %s' % (cid, result))
    return result


headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'
}
#进行验证码的识别：
#1.将验证码进行本地下载，将其提交给打码平台进行识别
url = 'http://www.renren.com/'
page_text = requests.get(url=url,headers=headers).text
#解析出验证码图片的url
tree = etree.HTML(page_text)
code_img_src = tree.xpath('//*[@id="verifyPic_login"]/@src')[0]
code_img_data = requests.get(url=code_img_src,headers=headers).content
with open('./code.jpg','wb') as fp:
    fp.write(code_img_data)
    
#将本地保存好的验证码图片交给打码平台识别
code_text = getCodeText(2004,'./code.jpg')


#模拟登录（发送post请求）
post_url = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=2019361852954'
data = {
    'email': 'www.zhangbowudi@qq.com',
    'icode': code_text,
    'origURL': 'http://www.renren.com/home',
    'domain': 'renren.com',
    'key_id': '1',
    'captcha_type': 'web_login',
    'password': '784601bfcb6b9e78d8519a3885c4a3de0aa7c3f597477e00d26a7aa6598e83bf',
    'rkey': '00313a9752665df609d455d36edfbe94',
    'f':'',
}
page_text = requests.post(url=post_url,headers=headers,data=data).text

with open('./renren.html','w',encoding='utf-8') as fp:
    fp.write(page_text)

三。proxies参数设置请求代理ip

代理：(快代理, 西刺代理, goubanjia)

类型：http与https

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
import random

if __name__ == "__main__":
    # 不同浏览器的UA
    header_list = [
        # 遨游
        {"user-agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)"},
        # 火狐
        {"user-agent": "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"},
        # 谷歌
        {
            "user-agent": "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"}
    ]
    # 不同的代理IP
    proxy_list = [
        {"http": "111.206.6.101:80"},
        {'http': '39.137.107.98:80'}
    ]
    # 随机获取UA和代理IP
    header = random.choice(header_list)
    proxy = random.choice(proxy_list)

    url = 'http://www.baidu.com/s?ie=UTF-8&wd=ip'
    # 参数3：设置代理
    response = requests.get(url=url, headers=header, proxies=proxy)
    response.encoding = 'utf-8'

    with open('daili.html', 'wb') as fp:
        fp.write(response.content)
    # 切换成原来的IP
    requests.get(url, proxies={"http": ""})

四。基于multiprocessing.dummy线程池的数据爬取

安装fake-useragent库:  pip install fake-useragent
需求：爬取梨视频的视频信息，并计算其爬取数据的耗时

import requests
import random
from lxml import etree
import re
from fake_useragent import UserAgent  #随机生成UA模块

# 安装fake-useragent库:pip install fake-useragent
url = 'http://www.pearvideo.com/category_1'
# 随机产生UA,如果报错则可以添加如下参数：
# ua = UserAgent(verify_ssl=False,use_cache_server=False).random
# 禁用服务器缓存：
# ua = UserAgent(use_cache_server=False)
# 不缓存数据：
# ua = UserAgent(cache=False)
# 忽略ssl验证：
# ua = UserAgent(verify_ssl=False)

ua = UserAgent().random
headers = {
    'User-Agent': ua
}
# 获取首页页面数据
page_text = requests.get(url=url, headers=headers).text
# 对获取的首页页面数据中的相关视频详情链接进行解析
tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@id="listvideoList"]/ul/li')
detail_urls = []
for li in li_list:
    detail_url = 'http://www.pearvideo.com/' + li.xpath('./div/a/@href')[0]
    title = li.xpath('.//div[@class="vervideo-title"]/text()')[0]
    detail_urls.append(detail_url)
for url in detail_urls:
    page_text = requests.get(url=url, headers=headers).text
    vedio_url = re.findall('srcUrl="(.*?)"', page_text, re.S)[0]
    
    data = requests.get(url=vedio_url, headers=headers).content
    fileName = str(random.randint(1, 10000)) + '.mp4'  # 随机生成视频文件名称
    with open(fileName, 'wb') as fp:
        fp.write(data)
        print(fileName + ' is over')

import requests
import random
from lxml import etree
import re
from fake_useragent import UserAgent

# 安装fake-useragent库:pip install fake-useragent
# 导入线程池模块
from multiprocessing.dummy import Pool

# 实例化线程池对象
pool = Pool()
url = 'http://www.pearvideo.com/category_1'
# 随机产生UA
ua = UserAgent().random
headers = {
    'User-Agent': ua
}
# 获取首页页面数据
page_text = requests.get(url=url, headers=headers).text
# 对获取的首页页面数据中的相关视频详情链接进行解析
tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@id="listvideoList"]/ul/li')

detail_urls = []  # 存储二级页面的url
for li in li_list:
    detail_url = 'http://www.pearvideo.com/' + li.xpath('./div/a/@href')[0]
    title = li.xpath('.//div[@class="vervideo-title"]/text()')[0]
    detail_urls.append(detail_url)

vedio_urls = []  # 存储视频的url
for url in detail_urls:
    page_text = requests.get(url=url, headers=headers).text
    vedio_url = re.findall('srcUrl="(.*?)"', page_text, re.S)[0]
    vedio_urls.append(vedio_url)
# 使用线程池进行视频数据下载
func_request = lambda link: requests.get(url=link, headers=headers).content
video_data_list = pool.map(func_request, vedio_urls)
# 使用线程池进行视频数据保存
func_saveData = lambda data: save(data)
pool.map(func_saveData, video_data_list)


def save(data):
    fileName = str(random.randint(1, 10000)) + '.mp4'
    with open(fileName, 'wb') as fp:
        fp.write(data)
        print(fileName + '已存储')


pool.close()
pool.join()