mathdatech/twoot
1
0
Fork 0
mirror of https://gitlab.com/jeancf/twoot.git synced 2024-11-30 15:31:11 +00:00
Code Issues 1 Packages Projects Releases Wiki Activity

Downloaded pics attachments

Browse Source
This commit is contained in:
jeancf 2020-12-18 11:45:43 +01:00
parent 14c24fe847
commit b4a596eff2
1 changed files with 27 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
twoot.py
View File

@ -48,12 +48,12 @@ logging.info('*********** NEW RUN ***********')
def process_media_body(tt_iter): def process_media_body(tt_iter):
''' """
Receives an iterator over all the elements contained in the tweet-text container. Receives an iterator over all the elements contained in the tweet-text container.
Processes them to make them suitable for posting on Mastodon Processes them to make them suitable for posting on Mastodon
:param tt_iter: iterator over the HTML elements in the text of the tweet :param tt_iter: iterator over the HTML elements in the text of the tweet
:return: cleaned up text of the tweet :return: cleaned up text of the tweet
''' """
tweet_text = '' tweet_text = ''
# Iterate elements # Iterate elements
for tag in tt_iter: for tag in tt_iter:
@ -80,11 +80,11 @@ def process_media_body(tt_iter):
def process_card(card_container): def process_card(card_container):
''' """
Extract image from card in case mastodon does not do it Extract image from card in case mastodon does not do it
:param card_container: soup of 'a' tag containing card markup :param card_container: soup of 'a' tag containing card markup
:return: list with url of image :return: list with url of image
''' """
list = [] list = []
link = card_container.get('href') link = card_container.get('href')
@ -95,12 +95,32 @@ def process_card(card_container):
return list return list
def process_attachments(attachments_container):
"""
Extract images or video from attachments. Videos are downloaded on the file system.
:param card_container: soup of 'div' tag containing attachments markup
:return: list with url of images
"""
# Collect url of images
pics = []
images = attachments_container.find_all('a', class_='still-image')
for image in images:
pics.append(image.get('href'))
# TODO Download nitter video (converted animated GIF)
# TODO Download twitter video
return pics
def contains_class(body_classes, some_class): def contains_class(body_classes, some_class):
''' """
:param body_classes: list of classes to search :param body_classes: list of classes to search
:param some_class: class that we are interested in :param some_class: class that we are interested in
:return: True if found, false otherwise :return: True if found, false otherwise
''' """
found = False found = False
for body_class in body_classes: for body_class in body_classes:
if body_class == some_class: if body_class == some_class:
@ -280,20 +300,12 @@ def main(argv):
# TODO Process attachment: capture image or .mp4 url or download twitter video # TODO Process attachment: capture image or .mp4 url or download twitter video
attachments_class = status.find('a', class_='attachments') attachments_class = status.find('a', class_='attachments')
if card_class is not None: if attachments_class is not None:
photos.extend(process_attachments(attachments_class)) photos.extend(process_attachments(attachments_class))
# Add footer with link to original tweet # Add footer with link to original tweet
tweet_text += '\n\nOriginal tweet : ' + full_status_url tweet_text += '\n\nOriginal tweet : ' + full_status_url
# Check if there are photos attached
media = status.find('div', class_='media')
if media:
# Extract photo url and add it to list
pic = str(media.img['src']).strip(':small')
photos.append(pic)
# If no media was specifically added in the tweet, try to get the first picture # If no media was specifically added in the tweet, try to get the first picture
# with "twitter:image" meta tag in first linked page in tweet text # with "twitter:image" meta tag in first linked page in tweet text
if not photos: if not photos: