github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[twitter] extract alt texts as 'description' (closes #2617)

Browse Source
This commit is contained in:
Mike Fährmann
2022-05-24 12:37:38 +02:00
parent 44ffc017ea
commit dcb580240d
1 changed files with 20 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
gallery_dl/extractor/twitter.py
View File

@@ -104,6 +104,7 @@ class TwitterExtractor(Extractor):
def _extract_media(self, tweet, entities, files): def _extract_media(self, tweet, entities, files):
for media in entities: for media in entities:
descr = media.get("ext_alt_text")
width = media["original_info"].get("width", 0) width = media["original_info"].get("width", 0)
height = media["original_info"].get("height", 0) height = media["original_info"].get("height", 0)
@@ -112,9 +113,10 @@ class TwitterExtractor(Extractor):
files.append({ files.append({
"url": "ytdl:{}/i/web/status/{}".format( "url": "ytdl:{}/i/web/status/{}".format(
self.root, tweet["id_str"]), self.root, tweet["id_str"]),
"width" : width, "width" : width,
"height" : height, "height" : height,
"extension": None, "extension" : None,
"description": descr,
}) })
elif self.videos: elif self.videos:
video_info = media["video_info"] video_info = media["video_info"]
@@ -123,22 +125,24 @@ class TwitterExtractor(Extractor):
key=lambda v: v.get("bitrate", 0), key=lambda v: v.get("bitrate", 0),
) )
files.append({ files.append({
"url" : variant["url"], "url" : variant["url"],
"width" : width, "width" : width,
"height" : height, "height" : height,
"bitrate" : variant.get("bitrate", 0), "bitrate" : variant.get("bitrate", 0),
"duration": video_info.get( "duration" : video_info.get(
"duration_millis", 0) / 1000, "duration_millis", 0) / 1000,
"description": descr,
}) })
elif "media_url_https" in media: elif "media_url_https" in media:
url = media["media_url_https"] url = media["media_url_https"]
base, _, fmt = url.rpartition(".") base, _, fmt = url.rpartition(".")
base += "?format=" + fmt + "&name=" base += "?format=" + fmt + "&name="
files.append(text.nameext_from_url(url, { files.append(text.nameext_from_url(url, {
"url" : base + self._size_image, "url" : base + self._size_image,
"width" : width, "width" : width,
"height" : height, "height" : height,
"_fallback": self._image_fallback(base), "_fallback" : self._image_fallback(base),
"description": descr,
})) }))
else: else:
files.append({"url": media["media_url"]}) files.append({"url": media["media_url"]})
@@ -711,6 +715,10 @@ class TwitterTweetExtractor(TwitterExtractor):
"options": (("syndication", True),), "options": (("syndication", True),),
"count": 1, "count": 1,
}), }),
# media alt texts / descriptions (#2617)
("https://twitter.com/my0nruri/status/1528379296041299968", {
"keyword": {"description": "oc"}
}),
) )
def __init__(self, match): def __init__(self, match):