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

[speakerdeck] inherit from GalleryExtractor

Browse Source
This commit is contained in:
Mike Fährmann
2024-06-15 21:56:51 +02:00
parent 4ffaa7fabf
commit ae3706286a
2 changed files with 24 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
gallery_dl/extractor/speakerdeck.py
View File

@@ -8,46 +8,35 @@
"""Extractors for https://speakerdeck.com/""" """Extractors for https://speakerdeck.com/"""
from .common import Extractor, Message from .common import GalleryExtractor
from .. import text from .. import text
import re import re
class SpeakerdeckPresentationExtractor(Extractor): class SpeakerdeckPresentationExtractor(GalleryExtractor):
"""Extractor for images from a presentation on speakerdeck.com""" """Extractor for images from a presentation on speakerdeck.com"""
category = "speakerdeck" category = "speakerdeck"
subcategory = "presentation" subcategory = "presentation"
directory_fmt = ("{category}", "{user}") directory_fmt = ("{category}", "{user}")
filename_fmt = "{presentation}-{num:>02}.{extension}" filename_fmt = "{presentation}-{num:>02}.{extension}"
archive_fmt = "{presentation}_{num}" archive_fmt = "{presentation}_{num}"
root = "https://speakerdeck.com"
pattern = r"(?:https?://)?(?:www\.)?speakerdeck\.com/([^/?#]+)/([^/?#]+)" pattern = r"(?:https?://)?(?:www\.)?speakerdeck\.com/([^/?#]+)/([^/?#]+)"
example = "https://speakerdeck.com/USER/PRESENTATION" example = "https://speakerdeck.com/USER/PRESENTATION"
def __init__(self, match): def __init__(self, match):
Extractor.__init__(self, match) GalleryExtractor.__init__(self, match, "")
self.user, self.presentation = match.groups() self.user, self.presentation = match.groups()
self.presentation_id = None
def items(self): def metadata(self, _):
data = self.get_job_metadata() url = self.root + "/oembed.json"
imgs = self.get_image_urls()
data["count"] = len(imgs)
yield Message.Directory, data
for data["num"], url in enumerate(imgs, 1):
yield Message.Url, url, text.nameext_from_url(url, data)
def get_job_metadata(self):
"""Collect metadata for extractor-job"""
url = "https://speakerdeck.com/oembed.json"
params = { params = {
"url": "https://speakerdeck.com/" + self.user + "url": "{}/{}/{}".format(self.root, self.user, self.presentation),
"/" + self.presentation,
} }
data = self.request(url, params=params).json() data = self.request(url, params=params).json()
self.presentation_id, pos = \ self.presentation_id = text.extr(
text.extract(data["html"], 'src="//speakerdeck.com/player/', '"') data["html"], 'src="//speakerdeck.com/player/', '"')
return { return {
"user": self.user, "user": self.user,
@@ -57,9 +46,10 @@ class SpeakerdeckPresentationExtractor(Extractor):
"author": data["author_name"], "author": data["author_name"],
} }
def get_image_urls(self): def images(self, _):
"""Extract and return a list of all image-urls""" url = "{}/player/{}".format(self.root, self.presentation_id)
page = self.request("https://speakerdeck.com/player/" + page = re.sub(r"\s+", " ", self.request(url).text)
self.presentation_id).text return [
page = re.sub(r"\s+", " ", page) (url, None)
return list(text.extract_iter(page, 'js-sd-slide" data-url="', '"')) for url in text.extract_iter(page, 'js-sd-slide" data-url="', '"')
]

8
test/results/speakerdeck.py
View File

@@ -15,6 +15,14 @@ __tests__ = (
"#pattern" : r"https://files.speakerdeck.com/presentations/50021f75cf1db900020005e7/slide_\d+.jpg", "#pattern" : r"https://files.speakerdeck.com/presentations/50021f75cf1db900020005e7/slide_\d+.jpg",
"#count" : 6, "#count" : 6,
"#sha1_content": "75c7abf0969b0bcab23e0da9712c95ee5113db3a", "#sha1_content": "75c7abf0969b0bcab23e0da9712c95ee5113db3a",
"author" : "Speaker Deck",
"count" : 6,
"num" : range(1, 6),
"presentation" : "introduction-to-speakerdeck",
"presentation_id": "50021f75cf1db900020005e7",
"title" : "Introduction to SpeakerDeck",
"user" : "speakerdeck",
}, },
) )