Podcast Fetching Scripts

九八新闻台_fetchRSS.py

import feedparser
import urllib
import requests
import sys
import os
import re
import subprocess

ParentPath = '/u/USER_ID/public_html/Podcast/九八新闻台/'
RSSFeed = 'https://feeds.soundcloud.com/users/soundcloud:users:496937352/sounds.rss'

feed = feedparser.parse(RSSFeed)

feed = feedparser.parse(RSSFeed)

# print(feed)

def get_valid_filename(s):
    """
    Return the given string converted to a string that can be used for a clean
    filename. Remove leading and trailing spaces; convert other spaces to
    underscores; and remove anything that is not an alphanumeric, dash,
    underscore, or dot.
    >>> get_valid_filename("john's portrait in 2004.jpg")
    'johns_portrait_in_2004.jpg'
    """
    s = str(s).strip().replace(' ', '_')
    return re.sub(r'(?u)[^-\w.]', '', s) 

print('Number of RSS posts: {}'.format(len(feed.entries)))


for episode in feed.entries:
    
    episode_title = episode['title'].replace("/", " ")
    # valid_filename = get_valid_filename(episode_title)  
    
    date = "{}_{}_{}_".format(episode['published_parsed'].tm_year,
                             episode['published_parsed'].tm_mon,
                             episode['published_parsed'].tm_mday)

    full_path = ParentPath + date + episode_title + ".mp3"

    if os.path.isfile(full_path):
        print("Skipping episode: {}".format(episode_title))
    else:
        print("Downloading episode: {}".format(episode_title))

        subprocess.run(["wget", episode['links'][1]['href'], "--output-document="+full_path, "-q", "-P", ParentPath])

        # print(episode['links'][1]['href'])        
        # requested_url = requests.get(episode['links'][1]['href'], timeout=5)
        # open((full_path), 'wb').write(requested_url.content)

股癌_fetchRSS.py

import feedparser
import urllib
import requests
import sys
import os
import re

ParentPath = '/u/USER_ID/public_html/Podcast/股癌/'
RSSFeed = 'https://feeds.soundon.fm/podcasts/954689a5-3096-43a4-a80b-7810b219cef3.xml'

feed = feedparser.parse(RSSFeed)

# print(feed)

def get_valid_filename(s):
    """
    Return the given string converted to a string that can be used for a clean
    filename. Remove leading and trailing spaces; convert other spaces to
    underscores; and remove anything that is not an alphanumeric, dash,
    underscore, or dot.
    >>> get_valid_filename("john's portrait in 2004.jpg")
    'johns_portrait_in_2004.jpg'
    """
    s = str(s).strip().replace(' ', '_')
    return re.sub(r'(?u)[^-\w.]', '', s) 

print('Number of RSS posts :{}'.format(len(feed.entries)))




for episode in feed.entries:
    
    episode_title = episode['title'].replace("/", " ")
    # valid_filename = get_valid_filename(episode_title)  
    
    full_path = ParentPath + episode_title + ".mp3"

    if os.path.isfile(full_path):
        print("Skipping episode: {}".format(episode_title))
    else:
        print("Downloading episode: {}".format(episode_title))
        requested_url = requests.get(episode['links'][1]['href'])
        open((full_path), 'wb').write(requested_url.content)

        
    











# print(feed.entries[0]['title_detail'])

# title = feed.entries[0]['title']
# print(title)

# print(type(title))

# print(feed.entries[0]['links'][1]['href'])

# requested_url = requests.get(feed.entries[0]['links'][1]['href'])

# open((feed.entries[0]['title']+".mp3").encode(sys.getfilesystemencoding()), 'wb').write(requested_url.content)





# real_mp3 = requested_url.
# print(r)


# urllib.request.Request(feed.entries[0]['links'][1]['href'])

# urllib.request.urlretrieve(feed.entries[0]['links'][1]['href'], "{}.mp3".format(feed.entries[0]['title']))