PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-09 03:37:52 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

Add function to save tweets in json format

Browse Source
This commit is contained in:
Rafael Lee 2022-11-30 01:25:10 +08:00
parent b9429b8c5e
commit 16970c041f
No known key found for this signature in database
GPG Key ID: 98C7A345120CD844
1 changed files with 26 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
src/you_get/extractors/twitter.py
View File

@ -52,6 +52,7 @@ def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs)
api_url = 'https://api.twitter.com/2/timeline/conversation/%s.json?tweet_mode=extended' % item_id api_url = 'https://api.twitter.com/2/timeline/conversation/%s.json?tweet_mode=extended' % item_id
api_content = get_content(api_url, headers={'authorization': authorization, 'x-guest-token': guest_token}) api_content = get_content(api_url, headers={'authorization': authorization, 'x-guest-token': guest_token})
info = json.loads(api_content) info = json.loads(api_content)
twitter_write_json(info, screen_name, item_id)
if item_id not in info['globalObjects']['tweets']: if item_id not in info['globalObjects']['tweets']:
# something wrong here # something wrong here
#log.wtf('[Failed] ' + info['timeline']['instructions'][0]['addEntries']['entries'][0]['content']['item']['content']['tombstone']['tombstoneInfo']['richText']['text'], exit_code=None) #log.wtf('[Failed] ' + info['timeline']['instructions'][0]['addEntries']['entries'][0]['content']['item']['content']['tombstone']['tombstoneInfo']['richText']['text'], exit_code=None)
@ -103,6 +104,7 @@ def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs)
api_url = 'https://api.twitter.com/1.1/statuses/show/%s.json?tweet_mode=extended' % item_id api_url = 'https://api.twitter.com/1.1/statuses/show/%s.json?tweet_mode=extended' % item_id
api_content = get_content(api_url, headers={'authorization': authorization, 'x-guest-token': guest_token}) api_content = get_content(api_url, headers={'authorization': authorization, 'x-guest-token': guest_token})
info = json.loads(api_content) info = json.loads(api_content)
twitter_write_json(info, screen_name, item_id)
media = info['extended_entities']['media'] media = info['extended_entities']['media']
for medium in media: for medium in media:
@ -129,6 +131,30 @@ def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs)
download_urls(urls, title, ext, size, output_dir, merge=merge) download_urls(urls, title, ext, size, output_dir, merge=merge)
def twitter_write_json(info, screen_name, item_id):
# this function save tweets in human readable json format
# # uncomment these lines if you need the original api returned json
# info_string = json.dumps(info, indent=" ", ensure_ascii=False)
# with open(screen_name+'_'+item_id+"_tweet.json", 'w') as fw:
# fw.write(info_string)
if 'globalObjects' in info.keys():
tweets = info['globalObjects']['tweets']
info_users = info["globalObjects"]['users']
tweets_simplified = {}
for key in tweets.keys():
user_id_str = tweets[key]['user_id_str']
tweets_simplified[key] = {}
tweets_simplified[key]['created_at'] = tweets[key]['created_at']
tweets_simplified[key]['user_id_str'] = tweets[key]['user_id_str']
tweets_simplified[key]['full_text'] = tweets[key]['full_text']
tweets_simplified[key]['name'] = info_users[user_id_str]['name']
tweet_string = json.dumps(
tweets_simplified, indent=" ", ensure_ascii=False)
with open(screen_name+'_'+item_id+".json", 'w') as fw:
fw.write(tweet_string)
site_info = "Twitter.com" site_info = "Twitter.com"
download = twitter_download download = twitter_download
download_playlist = playlist_not_supported('twitter') download_playlist = playlist_not_supported('twitter')