爬虫(1)

2023-11-13

# 使用urllib获取百度首页源码
import urllib.request

#1. 定义一个url(就是你要访问的地址)
url = 'http://www.baidu.com'

#2. 模拟浏览器向服务器发送请求
response = urllib.request.urlopen(url)

#3. 获取响应中的页面源码
#read方法 返回的是字节形式的二进制数据
#将二进制数据转换为字符串
#二进制--->字符串   解码 decode('编码的格式')
content = response.read().decode('utf-8')

#4. 打印数据
print(content)

在这里插入图片描述

# 使用urllib获取百度首页源码
import urllib.request

url = 'http://www.baidu.com'

#模拟浏览器向服务器发送请求
response = urllib.request.urlopen(url)

#3. 一个类型和六个方法
#response是HTTPResponse类型
print(type(response))

#按照一字节一字节读
content = response.read()
print(content)

#返回多少个字节
content = response.read(8)
print(content)

#读取一行
content = response.readline()
print(content)

#读取全部行
content = response.readlines()
print(content)

#返回状态码  如果是200了 证明逻辑没错
print(response.getcode())

#返回url地址
print(response.geturl())

#获取一个状态信息
print(response.getheaders())
import urllib.request

#下载网页
url_page = 'http://www.baidu.com'
urllib.request.urlretrieve(url_page,'baidu.html')

#下载图片
url_image = 'data:image/jpeg;base64,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'
urllib.request.urlretrieve(url_image,filename='Bently.jpg')

#下载视频
url_vedio ='https://www.bilibili.com/video/BV1MA411n7Fn?t=22.5'
urllib.request.urlretrieve(url_vedio,'威本联盟.mp4')

UA反爬

import urllib.request
url = 'https://www.baidu.com'

#url组成
#http/https

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36 Edg/112.0.1722.48'
}

#因为urlopen方法中不能存储字典,所以headers不能传递进去
#请求对象的定制!!!!!!!!!!!!
#注意:因为参数顺序问题,不能直接写urt和headers,中间有data,所以用关键字传参
request = urllib.request.Request(url=url,headers=headers)
response = urllib.request.urlopen(request)

content = response.read().decode('utf8')

print(content)

get请求quote方法

#获取 https://www.baidu.com/s?wd=%E5%91%A8%E6%9D%B0%E4%BC%A6周杰伦网页源码

import urllib.request

url = 'https://www.baidu.com/s?wd='

#请求对象定制为了解决反爬第一种手段
headers = {
    'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36 Edg/112.0.1722.48'
}

#将周杰伦三个字变成uicode编码格式
#使用urllib.parse
name = urllib.parse.quote('周杰伦')

url = url + name

#请求对象定制
request = urllib.request.Request(url=url,headers=headers)

#模拟浏览器向服务器发送请求
response = urllib.request.urlopen(request)

#获取相应内容
content = response.read().decode('utf8')

#打印数据
print(content)
#urlencode应用场景:多个参数
import urllib.parse

#https://www.baidu.com/s?wd=周杰伦&sex=男&location=中国

data = {
    'wd':'周杰伦',
    'sex':'男',
    'location':'中国台湾省'
}

a = urllib.parse.urlencode(data)
print(a)

在这里插入图片描述

#获取https://www.baidu.com/s?wd=%E5%91%A8%E6%9D%B0%E4%BC%A6&sex=%E7%94%B7网页源码
import urllib.request
import urllib.parse

base_url = 'https://www.baidu.com/s?'

data = {
    'wd':'周杰伦',
    'sex':'男',
    'location':'中国台湾省'
}

new_data = urllib.parse.urlencode(data)

url = base_url + new_data

headers = {
    'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36 Edg/112.0.1722.48'
}

#请求对象定制
request = urllib.request.Request(url=url,headers=headers)

#模拟浏览器向服务器发送请求
response = urllib.request.urlopen(request)

#获取相应内容
content = response.read().decode('utf8')

#打印数据
print(content)

requests模块(python中基于网络请求模块,作用:模拟浏览器发出请求)
1)urllib库
2)requests库

使用requests模块:
-指定url
-发起请求
-获取响应数据
-持久化存储

安装requests模块:pip install requests
在这里插入图片描述

爬取搜狗首页页面数据

import requests
#指定url
url = 'https://www.sogou.com/'
#发起请求
#get方法会返回一个响应对象
response = requests.get(url=url)
#获取相应数据
#.text返回的是字符串形式的响应数据
page_text = response.text
print(page_text)
#持久化存储
with open('./sogou.html','w',encoding='utf-8') as fp:
    fp.write(page_text)
print('爬取结束')

本文内容由网友自发贡献,版权归原作者所有,本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容,请联系:hwhale#tublm.com(使用前将#替换为@)

爬虫(1) 的相关文章

随机推荐