github/pelican
1
0
Fork 1
mirror of https://github.com/getpelican/pelican.git synced 2025-10-15 20:28:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Deal with broken embedded video links when importing from Tumblr (#3218)

Browse source 
Co-authored-by: boxydog <boxydog@users.noreply.github.com>
Co-authored-by: Will Thong <will@willthong.com>
This commit is contained in:
boxydog 2023-10-28 05:56:00 -05:00 • committed by GitHub
commit 9c87d8f3a3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 120 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

110
pelican/tests/test_importer.py
View file

@ -532,3 +532,113 @@ class TestTumblrImporter(TestWithOsDefaults):
['economics'], 'published', 'article', 'html')],
posts,
posts)
@patch("pelican.tools.pelican_import._get_tumblr_posts")
def test_video_embed(self, get):
def get_posts(api_key, blogname, offset=0):
if offset > 0:
return []
return [
{
"type": "video",
"blog_name": "testy",
"slug": "the-slug",
"date": "2017-07-07 20:31:41 GMT",
"timestamp": 1499459501,
"state": "published",
"format": "html",
"tags": [],
"source_url": "https://href.li/?https://www.youtube.com/a",
"source_title": "youtube.com",
"caption": "<p>Caption</p>",
"player": [
{
"width": 250,
"embed_code":
"<iframe>1</iframe>"
},
{
"width": 400,
"embed_code":
"<iframe>2</iframe>"
},
{
"width": 500,
"embed_code":
"<iframe>3</iframe>"
}
],
"video_type": "youtube",
}
]
get.side_effect = get_posts
posts = list(tumblr2fields("api_key", "blogname"))
self.assertEqual(
[('youtube.com',
'<p><a href="https://href.li/?'
'https://www.youtube.com/a">via</a></p>\n<p>Caption</p>'
'<iframe>1</iframe>\n'
'<iframe>2</iframe>\n'
'<iframe>3</iframe>\n',
'2017-07-07-the-slug',
'2017-07-07 20:31:41', 'testy', ['video'], [], 'published',
'article', 'html')],
posts,
posts)
@patch("pelican.tools.pelican_import._get_tumblr_posts")
def test_broken_video_embed(self, get):
def get_posts(api_key, blogname, offset=0):
if offset > 0:
return []
return [
{
"type": "video",
"blog_name": "testy",
"slug": "the-slug",
"date": "2016-08-14 16:37:35 GMT",
"timestamp": 1471192655,
"state": "published",
"format": "html",
"tags": [
"interviews"
],
"source_url":
"https://href.li/?https://www.youtube.com/watch?v=b",
"source_title": "youtube.com",
"caption":
"<p>Caption</p>",
"player": [
{
"width": 250,
# If video is gone, embed_code is False
"embed_code": False
},
{
"width": 400,
"embed_code": False
},
{
"width": 500,
"embed_code": False
}
],
"video_type": "youtube",
}
]
get.side_effect = get_posts
posts = list(tumblr2fields("api_key", "blogname"))
self.assertEqual(
[('youtube.com',
'<p><a href="https://href.li/?https://www.youtube.com/watch?'
'v=b">via</a></p>\n<p>Caption</p>'
'<p>(This video isn\'t available anymore.)</p>\n',
'2016-08-14-the-slug',
'2016-08-14 16:37:35', 'testy', ['video'], ['interviews'],
'published', 'article', 'html')],
posts,
posts)

12
pelican/tools/pelican_import.py
View file

@ -459,8 +459,16 @@ def tumblr2fields(api_key, blogname):
fmtstr = '<p><a href="%s">via</a></p>\n'
source = fmtstr % post.get('source_url')
caption = post.get('caption')
players = '\n'.join(player.get('embed_code')
for player in post.get('player'))
players = [
# If embed_code is False, couldn't get the video
player.get('embed_code') or None
for player in post.get('player')]
# If there are no embeddable players, say so, once
if len(players) > 0 and all(
player is None for player in players):
players = "<p>(This video isn't available anymore.)</p>\n"
else:
players = '\n'.join(players)
content = source + caption + players
elif type == 'answer':
title = post.get('question')