Mirrors/gallery-dl
1
0
Fork 0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-22 02:32:33 +01:00
Code Issues Releases Wiki Activity

[motherless] general tidying

Browse Source
This commit is contained in:
Smacking Potato 2024-11-21 01:36:02 +00:00
parent 5547955126
commit ab2a725e9c
1 changed files with 32 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

64
gallery_dl/extractor/motherless.py
View File

@ -77,7 +77,7 @@ class MotherlessMediaInGalleryExtractor(MotherlessMediaExtractor):
example = "https://motherless.com/GABC123/DEF456" example = "https://motherless.com/GABC123/DEF456"
def get_image(self): def get_image(self):
media_url, data = super().get_image() media_url, data = super().get_image()
data['gallery_id'] = re.match(self.pattern, self.url).group(1) data['gallery_id'] = re.match(self.pattern, self.url).group(1)
data['gallery_title'] = self.get_gallery_name(data['gallery_id']) data['gallery_title'] = self.get_gallery_name(data['gallery_id'])
data['title'] = get_media_title(self.page_data) data['title'] = get_media_title(self.page_data)
@ -107,22 +107,22 @@ class MotherlessGalleryImagesExtractor(MotherlessExtractor):
page = self.request(f"{self.root}/G{self.gallery_id}").text page = self.request(f"{self.root}/G{self.gallery_id}").text
data = { data = {
"gallery_id" : self.gallery_id, "gallery_id" : self.gallery_id,
"gallery_title": get_gallery_name_from_homepage(page), "gallery_title": get_gallery_name_from_homepage(page),
"uploader": get_gallery_uploader(page), "uploader": get_gallery_uploader(page),
"count": get_gallery_image_count(page)} "count": get_gallery_image_count(page)}
yield Message.Directory, data yield Message.Directory, data
for id, url, extension, title, num in get_images(self): for id, url, extension, title, num in get_images(self):
data |= { image_data = data | {
"id": id, "id": id,
"filename": id, "filename": id,
"extension": extension, "extension": extension,
"title": title, "title": title,
"num": num} "num": num}
yield Message.Url, url, data yield Message.Url, url, image_data
class MotherlessGalleryVideosExtractor(MotherlessExtractor): class MotherlessGalleryVideosExtractor(MotherlessExtractor):
@ -137,7 +137,7 @@ class MotherlessGalleryVideosExtractor(MotherlessExtractor):
self.gallery_id = re.match(self.pattern, self.url).group(1) self.gallery_id = re.match(self.pattern, self.url).group(1)
page = self.request(f"{self.root}/G{self.gallery_id}").text page = self.request(f"{self.root}/G{self.gallery_id}").text
data = { data = {
"gallery_id" : self.gallery_id, "gallery_id" : self.gallery_id,
"gallery_title": get_gallery_name_from_homepage(page), "gallery_title": get_gallery_name_from_homepage(page),
"uploader": get_gallery_uploader(page), "uploader": get_gallery_uploader(page),
"count": get_gallery_video_count(page)} "count": get_gallery_video_count(page)}
@ -145,14 +145,14 @@ class MotherlessGalleryVideosExtractor(MotherlessExtractor):
yield Message.Directory, data yield Message.Directory, data
for id, url, title, num in get_videos(self): for id, url, title, num in get_videos(self):
data |= { video_data = data | {
"id": id, "id": id,
"filename": id, "filename": id,
"extension": "mp4", "extension": "mp4",
"title": title, "title": title,
"num": num} "num": num}
yield Message.Url, url, data yield Message.Url, url, video_data
class MotherlessGalleryExtractor(MotherlessExtractor): class MotherlessGalleryExtractor(MotherlessExtractor):
@ -167,80 +167,80 @@ class MotherlessGalleryExtractor(MotherlessExtractor):
self.gallery_id = re.match(self.pattern, self.url).group(1) self.gallery_id = re.match(self.pattern, self.url).group(1)
page = self.request(f"{self.root}/G{self.gallery_id}").text page = self.request(f"{self.root}/G{self.gallery_id}").text
data = { data = {
"gallery_id" : self.gallery_id, "gallery_id" : self.gallery_id,
"gallery_title": get_gallery_name_from_homepage(page), "gallery_title": get_gallery_name_from_homepage(page),
"uploader": get_gallery_uploader(page), "uploader": get_gallery_uploader(page),
"count": get_gallery_image_count(page) + get_gallery_video_count(page)} "count": get_gallery_image_count(page) + get_gallery_video_count(page)}
yield Message.Directory, data yield Message.Directory, data
for id, url, extension, title, num in get_images(self): for id, url, extension, title, num in get_images(self):
data |= { image_data = data | {
"id": id, "id": id,
"filename": id, "filename": id,
"extension": extension, "extension": extension,
"title": title, "title": title,
"num": num} "num": num}
yield Message.Url, url, data yield Message.Url, url, image_data
for id, url, title, num in get_videos(self): for id, url, title, num in get_videos(self):
data |= { video_data = data | {
"id": id, "id": id,
"filename": id, "filename": id,
"extension": "mp4", "extension": "mp4",
"title": title, "title": title,
"num": num} "num": num}
yield Message.Url, url, data yield Message.Url, url, video_data
# Url extractors. # Url extractors.
def get_images(extractor): def get_images(extractor):
n = 1 page_number = 1
total_count = 0 total_image_count = 0
while True: while True:
page = extractor.request(f"{extractor.root}/GI{extractor.gallery_id}?page={n}").text page = extractor.request(f"{extractor.root}/GI{extractor.gallery_id}?page={page_number}").text
page_count = 0 page_image_count = 0
for result in re.finditer(' src="https://cdn5-thumbs\.motherlessmedia\.com/thumbs/([A-Z0-9]+?)\.([a-zA-Z]+)"[\s\S]+?alt="([^"]+)"', page): for result in re.finditer(' src="https://cdn5-thumbs\.motherlessmedia\.com/thumbs/([A-Z0-9]+?)\.([a-zA-Z]+)"[\s\S]+?alt="([^"]+)"', page):
id = result.group(1) id = result.group(1)
extension = result.group(2) extension = result.group(2)
url = f"https://cdn5-images.motherlessmedia.com/images/{id}.{extension}" url = f"https://cdn5-images.motherlessmedia.com/images/{id}.{extension}"
title = result.group(3) title = result.group(3)
page_count += 1 page_image_count += 1
yield id, url, extension, title, total_count + page_count yield id, url, extension, title, total_image_count + page_image_count
if page_count == 0: if page_image_count == 0:
return return
total_count += page_count total_image_count += page_image_count
n += 1 page_number += 1
def get_videos(extractor): def get_videos(extractor):
n = 1 page_number = 1
total_count = 0 total_video_count = 0
while True: while True:
page = extractor.request(f"{extractor.root}/GV{extractor.gallery_id}?page={n}").text page = extractor.request(f"{extractor.root}/GV{extractor.gallery_id}?page={page_number}").text
page_count = 0 page_video_count = 0
for result in re.finditer('thumbs/([A-Z0-9]+?)-strip\.jpg" alt="([^"]+)"', page): for result in re.finditer('thumbs/([A-Z0-9]+?)-strip\.jpg" alt="([^"]+)"', page):
id = result.group(1) id = result.group(1)
url = f"https://cdn5-videos.motherlessmedia.com/videos/{id}.mp4" url = f"https://cdn5-videos.motherlessmedia.com/videos/{id}.mp4"
title = result.group(2) title = result.group(2)
page_count += 1 page_video_count += 1
yield id, url, title, total_count + page_count yield id, url, title, total_video_count + page_video_count
if page_count == 0: if page_video_count == 0:
return return
total_count += page_count total_video_count += page_video_count
n += 1 page_number += 1
# Metadata extractors. # Metadata extractors.