python-scripts/modules/pod_dl/pod_dl.py at main · EricRa/python-scripts · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
"""
Podcast Downloader

Attempts to download every episode of a podcast in a given
RSS feed.

Note that this downloads the most recent episodes first, and you can
just cancel the script at any time if you don't want all the episodes.

Usage:

python pod_dl.py -u [URL]

Optionally, you can also provide the -t argument to return only the podcast
titles without actually downloading anything.
"""

import sys
import argparse

import feedparser
import requests


def dl_with_requests(link, filename):
    r2 = requests.get(link)
    # print(type(r2.content))
    # print(sys.getsizeof(r2.content))
    with open(filename, "wb") as f:
        f.write(r2.content)
        # print(sys.getsizeof(f))


def pod_dl(url, titles):
    # Check to see if RSS URL can be accessed and, if so, get the feed
    # using requests.  If not, return the http error code and end the program.
    try:
        r = requests.get(url)
    except Exception as e:
        print(
            f"There was an error: {e}.\n\nPlease ensure that a valid URL"
            " was provided."
        )
        sys.exit()

    status = r.status_code
    if status == 200:
        pass
    else:
        print(
            "There was a problem accessing the RSS feed.  HTTP Status "
            f"code {status} was returned.  Please ensure that the RSS URL"
            " provided is accessable from a web browser."
        )
        sys.exit()

    # Parse the feed with feedparser
    d = feedparser.parse(r.text)

    # check to see if titles argument is True.  If so, print a list of titles
    # and end the program
    if titles is True:
        for item in d.entries:
            print(item.title)
        sys.exit()
    else:
        pass

    # Download all episodes

    for item in d.entries:
        for link in item.enclosures:
            pod_url = link.get("href")
            #Obviously should refactor below at some point
            filename = item.title + ".mp3"
            filename = filename.replace(":", "-")
            filename = filename.replace(" ", "-")
            filename = filename.replace("/", "-")
            filename = filename.replace("?", "-")
            filename = filename.replace("\\", "-")
            filename = filename.replace("&", "and")
            filename = filename.replace("?", "-")
            filename = filename.replace("%", "-")
            filename = filename.replace(">", "-")
            filename = filename.replace("<", "-")
            filename = filename.replace("*", "-")
            filename = filename.replace("|", "-")
            filename = filename.replace("`", "-")
            filename = filename.replace("$", "-")

            # print(filename)
            print(f"Now downloading: {filename}")
            dl_with_requests(pod_url, filename)


# argument parser

parser = argparse.ArgumentParser(
    prog="podcast downloader",
    description="A password generator using the Python secrets module",
    epilog="",
)
parser.add_argument("-u", "--url", help="URL of the RSS feed")
parser.add_argument(
    "-t",
    "--titles",
    action="store_true",
    default=False,
    help=(
        "Will attempt to return the titles of all podcast episodes "
        "in the feed without actually downloading the episodes"
    ),
)

args = parser.parse_args()

# Run pod_dl function with given command line arguments
pod_dl(**vars(args))