python
python 爬取百思不得姐网站视频:http://www.budejie.com/video/
新建一个 py 文件,代码如下:
- #!/usr/bin/python
- # -*- coding: UTF-8 -*-
- import urllib,re,requests
- import sys
- reload(sys)
- sys.setdefaultencoding('utf-8')
- url_name = [] #url name
- def get():
- #获取源码
- hd = {"User-Agent":"Mozilla/5.0 (Windows NT 6.3; Win64; x64) ApplewebKit/537.36 (Khtml, like Gecko) Chrome/58.0.3029.110 Safari/537.36"}
- url = 'http://www.budejie.com/video/'
- html = requests.get(url,headers=hd).text
- url_content = re.compile(r'(<div class="j-r-list-c">.*?</div>.*?</div>)',re.S) #编译
- url_contents = re.findall(url_content,html) #匹配
- for i in url_contents:
- #匹配视频
- url_reg = r'data-mp4="(.*?)"' #视频地址
- url_items = re.findall(url_reg,i)
- #print url_items
- if url_items: #判断视频是否存在
- name_reg = re.compile(r'<a href="/detail-.{8}?.html">(.*?)</a>',re.S)
- name_items = re.findall(name_reg,i)
- #print name_items[0]
- for i,k in zip(name_items,url_items):
- url_name.append([i,k])
- print i,k
- for i in url_name: #i[1]=url i[0]=name
- urllib.urlretrieve(i[1],'video\\%s.mp4' % (i[0].decode('utf-8')))
- if __name__ == "__main__":
- get()
在 py 文件下新建一个 video 文件夹,执行后结果如下:
在 video 文件夹可以看到下载好的视频
注意报错:
UnicodeEncodeError: 'ascii' codec can't encode characters in position 0-9: ordinal not in range(128)
解决:
import sysreload(sys)sys.setdefaultencoding('utf-8')
来源: http://www.bubuko.com/infodetail-2085207.html