Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Output all attached images #31

Merged
merged 5 commits into from
Nov 13, 2022
Merged

Output all attached images #31

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
4c42925
Output all attached images
twoscomplement Nov 13, 2022
fe77995
Use equality comparison
twoscomplement Nov 13, 2022
5f800c5
Move evaluation of original_url out of loop
twoscomplement Nov 13, 2022
b42f410
Merge branch 'main' into twoscomplement-multiple-images
twoscomplement Nov 13, 2022
53b8ff3
remove accidental paste
twoscomplement Nov 13, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 9 additions & 8 deletions parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,33 +54,34 @@ def tweet_json_to_markdown(tweet, username, archive_media_folder, output_media_f
if 'url' in url and 'expanded_url' in url:
body = body.replace(url['url'], url['expanded_url'])
# replace image URLs with markdown image links to local files
if 'entities' in tweet and 'media' in tweet['entities']:
for media in tweet['entities']['media']:
if 'entities' in tweet and 'media' in tweet['entities'] and 'extended_entities' in tweet and 'media' in tweet['extended_entities']:
original_url = tweet['entities']['media'][0]['url']
markdown = ''
for media in tweet['extended_entities']['media']:
if 'url' in media and 'media_url' in media:
original_url = media['url']
original_expanded_url = media['media_url']
original_filename = os.path.split(original_expanded_url)[1]
local_filename = os.path.join(archive_media_folder, tweet_id_str + '-' + original_filename)
new_url = output_media_folder_name + tweet_id_str + '-' + original_filename
markdown += '' if not markdown and body == original_url else '\n\n'
if os.path.isfile(local_filename):
# Found a matching image, use this one
if not os.path.isfile(new_url):
shutil.copy(local_filename, new_url)
markdown = f'![]({new_url})'
markdown += f'![]({new_url})'
else:
# Is there any other file that includes the tweet_id in its filename?
media_filenames = glob.glob(os.path.join(archive_media_folder, tweet_id_str + '*'))
if len(media_filenames) > 0:
markdown = ''
for media_filename in media_filenames:
media_url = f'{output_media_folder_name}{os.path.split(media_filename)[-1]}'
if not os.path.isfile(media_url):
shutil.copy(media_filename, media_url)
markdown += f'\n\n<video controls><source src="{media_url}">Your browser does not support the video tag.</video>\n{media_url}'
markdown += f'<video controls><source src="{media_url}">Your browser does not support the video tag.</video>\n{media_url}'
else:
print(f'Warning: missing local file: {local_filename}. Using original link instead: {original_url} (expands to {original_expanded_url})')
markdown = f'![]({original_url})'
body = body.replace(original_url, markdown)
markdown += f'![]({original_url})'
body = body.replace(original_url, markdown)
twoscomplement marked this conversation as resolved.
Show resolved Hide resolved
# append the original Twitter URL as a link
body += f'\n\n(Originally on Twitter: [{timestamp_str}](https://twitter.com/{username}/status/{tweet_id_str}))'
return timestamp, body
Expand Down