comments, cleanup and graceful fail in case of rss download issues
This commit is contained in:
@@ -4,9 +4,13 @@ from defusedxml.ElementTree import fromstring
|
||||
import urllib.request
|
||||
import datetime
|
||||
|
||||
# rss-xml URL
|
||||
url = "https://www1.wdr.de/mediathek/audio/zeitzeichen/zeitzeichen-podcast-100.podcast"
|
||||
|
||||
def findZander(today):
|
||||
"""
|
||||
"""
|
||||
# find metadata
|
||||
for n, item in enumerate(today):
|
||||
if item.tag.find("title") >= 0:
|
||||
title = today[n].text
|
||||
@@ -15,31 +19,36 @@ def findZander(today):
|
||||
if item.tag.find("enclosure") >= 0:
|
||||
podcasturl = today[n].attrib["url"]
|
||||
|
||||
# check for Zander
|
||||
if author.find("Zander") >= 0:
|
||||
print(f"ZanderAlert: {title}\nDownload-URL: {podcasturl}")
|
||||
return {"url": podcasturl, "title": title, "full_item": today}
|
||||
return None
|
||||
|
||||
# read rss feed
|
||||
with urllib.request.urlopen(url) as response:
|
||||
assert response.status == 200, f"Webrequest fehlgeschlagen, stimmt die URL noch?"
|
||||
feed = fromstring(response.read())[0]
|
||||
|
||||
# read entries in rss feed until first entry (today)
|
||||
for i in feed:
|
||||
if i.tag == "item":
|
||||
metadata = findZander(i)
|
||||
break
|
||||
|
||||
# future feature: episode download and feed regeneration
|
||||
|
||||
# download episode download and regenerate zanderzeichen feed
|
||||
if metadata is not None:
|
||||
# wdrzeitzeichen_2017-05-16_Voltaire wird verhaftet_16051717_wdr5.mp3
|
||||
day, month, year = datetime.datetime.now().strftime("%d.%m.%Y").split(".")
|
||||
title = metadata["title"]
|
||||
for i in (",", "(", ")"):
|
||||
for i in (",", "(", ")"): # get rid of unwanted characters in title
|
||||
title = title.replace(i, "")
|
||||
refdate = title.split(" ")[-1].replace(".", "")
|
||||
title = " ".join(title.split(" ")[:-1])
|
||||
refdate = title.split(" ")[-1].replace(".", "") # generate reference date
|
||||
title = " ".join(title.split(" ")[:-1]) # strip reference date
|
||||
|
||||
# destination file name
|
||||
destination = f"files/wdrzeitzeichen_{year}-{month}-{day}_{title}_{refdate}_wdr5.mp3"
|
||||
urllib.request.urlretrieve(metadata["url"], "test/"+destination)
|
||||
# actual download of file
|
||||
urllib.request.urlretrieve(metadata["url"], destination)
|
||||
|
||||
# regenerate zanderzeichen feed
|
||||
import genfeed
|
||||
|
||||
Reference in New Issue
Block a user