爬虫 -requests

requests模块

- 1.什么是requests模块
    - python原生一个基于网络请求的模块，模拟浏览器发起请求。
- 2.为什么要使用requests模块
    - 1.自动处理url编码 
    - 2.自动处理post请求的参数
    - 3.简化cookie的代理的操作：
        cookie操作：
        - 创建一个cookiejar对象
        - 创建一个handler对象
        - 创建一个operner
        
        代理操作：
        - 创建handler对象，代理ip和端口封装到该对象
        - 创建openner对象
- 3.requests如何被使用
    - 安装：pip install  requests
    - 使用流程：
        - 1.指定url
        - 2.使用requests模块发起请求
        - 3.获取响应数据
        - 4.进行持久化存储
- 4.通过5个基于requests模块的爬虫项目对该模块进行系统学习和巩固
    - get请求
    - post请求
    - ajax的get
    - ajax的post
    - 综合
    - cookie
    - 代理

---

1 基于requests模块发起get请求

- 需求：爬取搜狗首页的页面数据

import requests
#指定url
url = 'https://www.sogou.com/'

#发起get请求:get方法会返回请求成功的相应对象
response = requests.get(url=url)

#获取响应中的数据值:text可以获取响应对象中字符串形式的页面数据
page_data = response.text

print(page_data)

#持久化操作
with open('./sougou.html','w',encoding='utf-8') as fp:
    fp.write(page_data)

response对象中其他重要的属性

#response对象中其他重要的属性
import requests
#指定url
url = 'https://www.sogou.com/'

#发起get请求:get方法会返回请求成功的相应对象
response = requests.get(url=url)

#content获取的是response对象中二进制（byte）类型的页面数据
# print(response.content)
#返回一个响应状态码
# print(response.status_code)
#返回响应头信息
# print(response.headers)
#获取请求的url
# print(response.url)

https://www.sogou.com/

• requests模块如何处理携带参数的get请求
  方式1：
  • 需求：指定一个词条，获取搜狗搜索结果所对应的页面数据

import requests

url = 'https://www.sogou.com/web?query=周杰伦&ie=utf-8'

response = requests.get(url=url)

page_text = response.text

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

# 自定义请求头信息
import requests
url = 'https://www.sogou.com/web'

#将参数封装到字典中
params = {
    'query':'周杰伦',
    'ie':'utf-8'
}
#自定义请求头信息
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
}

response = requests.get(url=url,params=params,headers=headers)

response.status_code

200

---

2 基于requests模块发起的post请求

- 需求：登录豆瓣网，获取登录成功后的页面数据

import requests

#1.指定post请求的url
url = 'https://accounts.douban.com/login'

#封装post请求的参数
data = {
    "source": "movie",
    "redir": "https://movie.douban.com/",
    "form_email": "15027900535",
    "form_password": "bobo@15027900535",
    "login": "登录",
}
#自定义请求头信息
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
}
#2.发起post请求
response = requests.post(url=url,data=data,headers=headers)

#3.获取响应对象中的页面数据
page_text = response.text

#4.持久化操作
with open('./douban.html','w',encoding='utf-8') as fp:
    fp.write(page_text)

基于ajax的get请求

-需求：抓取豆瓣电影上电影详情的数据

import requests

url = 'https://movie.douban.com/j/chart/top_list?'

#封装ajax的get请求中携带的参数
params = {
    'type':'5',
    'interval_id':'100:90',
    'action':'',
    'start':'200',
    'limit':'20'
}
#自定义请求头信息
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
}

response = requests.get(url=url,params=params,headers=headers)

# print(response.text)

基于ajax的post请求

- 需求：爬去肯德基城市餐厅位置数据

import requests

#1指定url
post_url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword'

#处理post请求的参数
data = {
    "cname": "",
    "pid": "",
    "keyword": "上海",
    "pageIndex": "1",
    "pageSize": "10",
}
#自定义请求头信息
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
}

#2发起基于ajax的post请求
response = requests.post(url=post_url,headers=headers,data=data)

response.text

'{"Table":[{"rowcount":28}],"Table1":[{"rownum":1,"storeName":"开发区上海路","addressDetail":"开发区上海路80号乐天玛特超一楼","pro":"Wi-Fi,礼品卡,生日餐会","provinceName":"江苏省","cityName":"南通市"},{"rownum":2,"storeName":"太仓新区东亭路","addressDetail":"太仓市娄江路与县府街交叉口西南侧（太仓新区上海路北、东亭路东地块）万达广场","pro":"Wi-Fi,店内参观,礼品卡,生日餐会","provinceName":"江苏省","cityName":"苏州市"},{"rownum":3,"storeName":"动力南广场（汇金奥特莱斯B1层）","addressDetail":"石龙路750-3号上海南站地下商场南馆","pro":"精选店,礼品卡","provinceName":"上海市","cityName":"上海市"},{"rownum":4,"storeName":"谷阳","addressDetail":"松汇中路568号上海鹿都商业广场","pro":"Wi-Fi,店内参观,礼品卡,生日餐会,溯源","provinceName":"上海市","cityName":"上海市"},{"rownum":5,"storeName":"南广场","addressDetail":"秣陵路303号上海火车站西南出口一侧","pro":"Wi-Fi,礼品卡","provinceName":"上海市","cityName":"上海市"},{"rownum":6,"storeName":"北广场","addressDetail":"秣陵路303号上海站北广场北立面1F大厅入口西侧位置","pro":"Wi-Fi","provinceName":"上海市","cityName":"上海市"},{"rownum":7,"storeName":"南站精选（火车站站内）","addressDetail":"沪闵路9001号上海南站候车大厅","pro":"精选店,礼品卡","provinceName":"上海市","cityName":"上海市"},{"rownum":8,"storeName":"上海滩","addressDetail":"佘山林湖路888号-1上海滩区5号","pro":"精选店,礼品卡","provinceName":"上海市","cityName":"上海市"},{"rownum":9,"storeName":"动力南精选（3号线2号出口）","addressDetail":"沪闵路9001号上海南站（1F三角地A-1）一层","pro":"精选店,礼品卡","provinceName":"上海市","cityName":"上海市"},{"rownum":10,"storeName":"上海南路","addressDetail":"上海南路3号699生活空间3号楼","pro":"Wi-Fi,店内参观,礼品卡,生日餐会","provinceName":"江西省","cityName":"南昌市"}]}'

3 综合项目实战

- 需求：爬取搜狗知乎某一个词条对应一定范围页码表示的页面数据

import os

#前三页页面数据（1，2，3）
import requests
import os

#创建一个文件夹
if not os.path.exists('./pages'):
    os.mkdir('./pages')
    
word = input('enter a word:')

#动态指定页码的范围
start_pageNum = int(input('enter a start pageNum:'))
end_pageNum = int(input('enter a end pageNum:'))
#自定义请求头信息
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
}
#1.指定url:设计成一个具有通用的url
url = 'https://zhihu.sogou.com/zhihu'
for page in range(start_pageNum,end_pageNum+1):
    param = {
        'query':word,
        'page':page,
        'ie':'utf-8'
    }
    response = requests.get(url=url,params=param,headers=headers)
    
    #获取响应中的页面数据（指定页码（page））
    page_text = response.text
    
    #进行持久化存储
    fileName = word+str(page)+'.html'
    filePath = 'pages/'+fileName
    with open(filePath,'w',encoding='utf-8') as fp:
        fp.write(page_text)
        print('第%d页数据写入成功'%page)
    
    

enter a word:python
enter a start pageNum:3
enter a end pageNum:5
第3页数据写入成功
第4页数据写入成功
第5页数据写入成功

---

4 cookie：

- cookie：
    基于用户的用户数据
    - 需求：爬取张三用户的豆瓣网的个人主页页面数据
- cookie作用：服务器端使用cookie来记录客户端的状态信息。
实现流程：
    1.执行登录操作（获取cookie）
    2.在发起个人主页请求时，需要将cookie携带到该请求中
    注意：session对象：发送请求（会将cookie对象进行自动存储）
- 代理：

#问题：没有获取个人主页的页面数据
#原因：爬虫程序没有严格遵从浏览器的请求流程
import requests

#1.指定url
url = 'https://www.douban.com/people/185687620/'
headers={
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
    }
#2.发起请求
response = requests.get(url=url,headers=headers)

#3.获取页面数据
page_text = response.text

#4.持久化存储
with open('./douban.html','w',encoding='utf-8') as fp:
    fp.write(page_text)

import requests

session = requests.session()
#1.发起登录请求：将cookie获取，切存储到session对象中
login_url = 'https://accounts.douban.com/login'
data = {
    "source": "None",
    "redir": "https://www.douban.com/people/185687620/",
    "form_email": "15027900535",
    "form_password": "bobo@15027900535",
    "login": "登录",
}
headers={
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
    }
#使用session发起post请求
login_response = session.post(url=login_url,data=data,headers=headers)

#2.对个人主页发起请求（session（cookie）），获取响应页面数据
url = 'https://www.douban.com/people/185687620/'
response = session.get(url=url,headers=headers)
page_text = response.text

with open('./douban110.html','w',encoding='utf-8') as fp:
    fp.write(page_text)

---

5 代理操作：

- 1.代理：第三方代理本体执行相关的事物。生活：代购，微商，中介
- 2.为什么要使用代理？
    - 反爬操作。
    - 反反爬手段
- 3.分类：
    - 正向代理：代替客户端获取数据
    - 反向代理：代理服务器端提供数据
- 4.免费代理ip的网站提供商：
    - www.goubanjia.com
    - 快代理
    - 西祠代理
- 5.代码：

import requests

url = 'http://www.baidu.com/s?ie=utf-8&wd=ip'

headers={
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
    }

#将代理ip封装到字典
proxy = { 
    'http':'77.73.69.120:3128'
}
#更换网路IP
response = requests.get(url=url,proxies=proxy,headers=headers)

with open('./daili.html','w',encoding='utf-8') as fp:
    fp.write(response.text)