爬虫入门 0x00 单页面抓取文件

本文共 339 字，预计阅读时间 1 分钟。

抓取一个页面上指定类型的文件并保存。
最后一版Python2.7写的代码，之后就开始用3.6了。
最后一版不会用re写的代码，之后……之后大概也没怎么学吧。

# Author = Cyrus# Py Edition = 2.7import requests
import os

os.system("cls")
global success
success=0
global error
error=0

def download(url,filename):
    global success
    global error
    s=requests.get(url,stream=True)
    if (s.status_code==200):
        with open(filename, 'wb') as f:
            for chunk in s:
                f.write(chunk)
        print ' - Sucess'
        success+=1
    else:
        print ' - Error'
        error+=1

def find(url,a,path):
    print "******************************************"
    print "URL      = ",url
    print "FILETYPE = ",a
    s=requests.post(url=url).content
    while (s.partition(a)[1]!=""):
        r1=url+s.partition(a)[0]
        while (r1.partition("\"")[1]!=""):
            r1=r1.partition("\"")[2]
        filename=r1
        while (filename.partition("/")[1]!=""):
            filename=filename.partition("/")[2]
        filename=path+filename+a
        if (r1.partition("http://")[1]!=""):
            r1=r1+a
        else:
            r1=url+r1+a
        print r1,
        download(r1,filename)
        s=s.partition(a)[2]
    print ""

url="http://www.uestc.edu.cn/"
find(url,".jpg","")
find(url,".png","")
find(url,".html","")

print "******************************************"
print "Success download ",success," file(s),"
print "Failed download ",error," file(s)."

【运行】