Created
November 9, 2016 05:39
Star
You must be signed in to star a gist
python sript to grab .mp3 url from a html page/ web page
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from bs4 import BeautifulSoup | |
import os | |
try: | |
import urllib.request as urllib2 | |
except ImportError: | |
import urllib2 | |
import sys | |
#Souce html from which the you want stuff to download | |
source_url = "http://www.mayuren.org/site/mayurengorg/1Tamil/Audio%20Books%20-%20Tamil%20Collection/ponniyin%20selvan/ponni%201" | |
#write url as text file to download it with Aria2c downloader, remember to make it in aria2c folder and create the fil urls.txt | |
aria2c_filepath = "C:/Users/User2/Desktop/aria2-1.28.0-win-64bit-build1/urls.txt" | |
html_page = urllib2.urlopen(source_url) | |
soup = BeautifulSoup(html_page) | |
#print All links in the html pages, i used for my first execution to analyse the url and write the rule for it. | |
''' | |
for all_links in soup.findAll('a'): | |
the_url = all_links.get('href') | |
print(the_url) ''' | |
#Deleting existing contents from the file | |
f = open(aria2c_filepath, 'w') | |
f.close() | |
for link in soup.findAll('a'): | |
temp_reader = link.get('href') | |
if(temp_reader!=None): | |
if(".mp3?l=12" in temp_reader): | |
url = ("http://www.mayuren.org"+temp_reader).split("?l=12")[0]; | |
with open(aria2c_filepath, 'a') as f: | |
print(url, file=f) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment