day 3 爬虫实战练习

爬取文本网页

import requests   #导入requesets库
#往百度主页发送请求，获取响应对象
response=requests.get(url='https://www.baidu.com/')
#设置字符编码为 utf-8
response.encoding='utf-8'
#打印响应文本
print(response.text)
#把响应文本写入本地
with open('baidu.html','w',encoding='utf-8') as f:
    f.write(response.text)

爬取视频

import requests

response =requests.get('https://vd4.bdstatic.com/mda-ij7mjzskvmwpyb6q/sc/mda-ij7mjzskvmwpyb6q.mp4')
print(response.content)
with open('张艺兴.mp4','wb')as f:
     f.write(response.content)

1.先往梨视频主页发送请求

http://www.pearvideo.com/

　　解析获取所有视频的id

     video_1570302

　　re.findall()

2.获取视频详情页url

 .........................

 .........................

re正则，用于解析文本数据

1.先往梨视频主页发送请求

re正则匹配获取所有的视频id

参数1；正则匹配规则

参数2：解析文本

参数3：匹配模式

import requests
import  re
reponse=requests.get('http://www.pearvideo.com/')
print(reponse.text)
res_list=re.findall('<a href=video_(.*?)"',reponse.text,re.S)
print(res_list)

for v_id in res_list:
     detail_url='http://www.pearvideo.com/video_'+v_id
     print(detail_url)

import requests
import  re
reponse=requests.get('http://www.pearvideo.com/')
print(reponse.text)
res_list=re.findall('<a href=video_(.*?)"',reponse.text,re.S)
print(res_list)

for v_id in res_list:
     detail_url='http://www.pearvideo.com/video_'+v_id
     #print(detail_url)
#对每一个视频详情页发送请求获取视频，频源url
response =requests.get(url=detail_url)
print(response.text)
#解析并提取详情页视频url
#视频url
video_url=re.findall('srcUrl="(.*?)'"),response.text,re.S)[0]
print(video_url)
#视频名称
video_name=re.findall('<h1 class="video-tt(.*?)</h1>',response.text,re.S)[0]
print(video_name)

#往视频url发送请求获取视频二进制流
v_response=requests.get(video_url)
with open('%s.mp4'%video_name,'wb')as f:
     f.write(v_response.content)
     print(video_name,'视频爬取完成')