PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-01-23 21:45:02 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[twitter] prioritize (main) images over videos

Browse Source
This commit is contained in:
Mort Yao 2015-12-10 09:56:50 +01:00
parent c386a424df
commit e5922a9182
1 changed files with 23 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
src/you_get/extractors/twitter.py
View File

@ -11,28 +11,9 @@ def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs)
item_id = r1(r'data-item-id="([^"]*)"', html)
page_title = "{} [{}]".format(screen_name, item_id)
try: # extract video
icards = r1(r'data-src="([^"]*)"', html)
if icards:
card = get_html("https://twitter.com" + icards)
data_player_config = r1(r'data-player-config="([^"]*)"', card)
if data_player_config is None:
vine_src = r1(r'<iframe src="([^"]*)"', card)
vine_download(vine_src, output_dir=output_dir, merge=merge, info_only=info_only)
return
data = json.loads(unescape_html(data_player_config))
source = data['playlist'][0]['source']
else:
source = r1(r'<source video-src="([^"]*)"', html)
mime, ext, size = url_info(source)
print_info(site_info, page_title, mime, size)
if not info_only:
download_urls([source], page_title, ext, size, output_dir, merge=merge)
except: # extract images
urls = re.findall(r'property="og:image"\s*content="([^"]+)"', html)
try: # extract images
urls = re.findall(r'property="og:image"\s*content="([^"]+:large)"', html)
assert urls
images = []
for url in urls:
url = ':'.join(url.split(':')[:-1]) + ':orig'
@ -57,6 +38,26 @@ def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs)
download_urls([url], title, ext, size,
output_dir=output_dir)
except: # extract video
icards = r1(r'data-src="([^"]*)"', html)
if icards:
card = get_html("https://twitter.com" + icards)
data_player_config = r1(r'data-player-config="([^"]*)"', card)
if data_player_config is None:
vine_src = r1(r'<iframe src="([^"]*)"', card)
vine_download(vine_src, output_dir=output_dir, merge=merge, info_only=info_only)
return
data = json.loads(unescape_html(data_player_config))
source = data['playlist'][0]['source']
else:
source = r1(r'<source video-src="([^"]*)"', html)
mime, ext, size = url_info(source)
print_info(site_info, page_title, mime, size)
if not info_only:
download_urls([source], page_title, ext, size, output_dir, merge=merge)
site_info = "Twitter.com"
download = twitter_download
download_playlist = playlist_not_supported('twitter')