爬虫中什么是requests

print(response.text)       #响应的信息
print(response.headers)  #获取响应头
print(response.status_code)  #响应状态码
print(response.encoding)   #响应的编码
print(response.cookies)   #获取cookies信息

带参数GET请求

data = {
    'name':'abc'，
''''''
}

response = requests.get(url='http://www.baidu.com',params=data)

解析json

import requests

response = requests.get(url='http://www.baidu.com')
print(response.json())

获取二进制数据

import requests

response = requests.get(url='http://www.baidu.com')
print(response.content)

高级操作

文件上传

import requests
flies = {
    'flies':open('XXX','rb')
}
response = requests.post(url='http://www.baidu.com',flies=flies)
print(response.content)

会话维持 （模拟登陆）

import requests

s = requests.Session()
s.get('http://httpbin.org/cookies/set/number/123456789')
response = s.get('http://httpbin.org/cookies')
print(response.text)

{
  "cookies": {
    "number": "123456789"
  }
}

证书验证

import requests
import urllib3

url = 'https://www.biqudu.com/43_43821/2520338.html'
urllib3.disable_warnings() #关闭证书后再把警告提示关闭
response = requests.get(url=url,verify=False)
print(response.text)

代理认证

url = 'https://www.biqudu.com/43_43821/2520338.html'
proxies = {
    'http':'http://127.0.0.2',   
    'https':'http://user:pwd@127.0.0.2',  #带密码的代理
}

response = requests.get(url=url,proxies=proxies)
print(response.text)
    ****

请求超时处理

import requests
from requests.exceptions import ReadTimeout  #导入错误模块

url = 'https://www.taobao.com'
try:
    response = requests.get(url=url,timeout=0.1)  #限制请求时间
    print(response.status_code)
except ReadTimeout:
    print('请求超时')

认证设置

#有的网站打开的瞬间就需要密码认证

import requests
from requests.auth import HTTPBasicAuth

url = 'https://www.taobao.com'

response = requests.get(url=url,auth=('user','pwd'))
print(response.status_code)

1，笔趣阁小说（入门级爬取文本信息）

抓取笔趣阁小说：排行榜单的小说总榜

1.请求初始url，获取网页源码
2.解析网页源码，得到文本内容
3.将小说全部章节名存入txt文件中

from lxml import etree
import requests

url = 'http://www.biqiuge.com/paihangbang'

response = requests.get(url)
response.encoding = response.apparent_encoding


html = etree.HTML(response.text)
info = html.xpath("//div[@class='block bd'][1]/ul[@class='tli']/li/a")
for i in info:
    title = i.xpath("./text()")[0]
    urls =i.xpath("./@href")[0]
    urls1 = 'http://www.biqiuge.com'+urls

    with open(title+'.txt','w+',encoding='utf-8') as f:
        response1 = requests.get(url=urls1)
        response1.encoding = response1.apparent_encoding
        html = etree.HTML(response1.text)
        info = html.xpath("//div[@class='listmain']/dl/dd/a/text()")[6:]
        for i in info:
            f.write(i.strip()+'
')
        print(title+"------写入成功")

------------------------------------------------------
判断路径是否存在，自动创建！！！
if not os.path.exists(title):
    os.mkdir(title)

path = os.path.join(title,title1)

if not os.path.exists(path):
    os.mkdir(path)

with open(path+ '\' + title2 +'.txt', 'w+', encoding='utf-8') as f:
    for con in contents:
        f.write(con.strip() + '
')
    print(title +'---'+ title1 +'---'+ title2 + '---写入成功')

2，崔庆才博客（伪造头信息爬取策略）

from lxml import etree

import requests
n = 0
with open('cuijincai.txt', 'w+', encoding='utf-8') as f:
    for i in range(1,10):
        url = 'https://cuiqingcai.com/category/technique/python/page/'+str(i)
#这里的循环，该网站是动态显示，可以在f12/network中XHR中查到该链接url。
        headers = {

        Referer: https://cuiqingcai.com/category/technique/python
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36'
        }
    #部分网站设置反爬机制，可以为请求头设置 信息
        response = requests.get(url=url,headers=headers)
        html = etree.HTML(response.text)
        all_div = html.xpath("//article[@class='excerpt']")

        for div in  all_div:
            title = div.xpath("./header/h2/a/text()")[0]  #当前路径下的标题信息
            author = div.xpath("./p[@class='auth-span']/span[@class='muted'][1]/a/text()")[0]
            time = div.xpath("./p[@class='auth-span']/span[@class='muted'][2]/text()")[0]
            liulanshu = div.xpath("./p[@class='auth-span']/span[@class='muted'][3]/text()")[0]
            pinlun = div.xpath("./p[@class='auth-span']/span[@class='muted'][4]/a/text()")[0]
            like = div.xpath("./p[@class='auth-span']/span[@class='muted'][5]/a[@id='Addlike']/span[@class='count']/text()")[0]+'喜欢'
            n += 1
            f.write("第{}条	{}	{}	{}	{}	{}	{}
".format(n,title,author,time,liulanshu,pinlun,like))

User Agent中文名为用户代理，简称 UA，它是一个特殊字符串头，使得服务器能够识别客户使用的操作系统及版本、CPU 类型、浏览器及版本、
浏览器渲染引擎、浏览器语言、浏览器插件等。

HTTP Referer是header的一部分，当浏览器向web服务器发送请求的时候，一般会带上Referer，告诉服务器我是从哪个页面链接过来的，
服务器基此可以获得一些信息用于处理。

https://www.liaoxuefeng.com  该网站设置反爬，可以用上面设置头信息爬取