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

fix(mangafreak): fix image extraction and simplify code

Browse Source 
- Fix image URL extraction pattern to handle img tags with id attribute
- Use self.groups pattern instead of custom __init__ methods
- Fix chapter list extraction to use correct table structure
This commit is contained in:
Duy Nguyen
2026-01-25 17:24:05 +01:00
parent 8b0e8c656d
commit 58662f900a
1 changed files with 25 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
gallery_dl/extractor/mangafreak.py
View File

@@ -25,35 +25,30 @@ class MangafreakChapterExtractor(MangafreakBase, ChapterExtractor):
pattern = BASE_PATTERN + r"(/Read1_(.+)_(\d+[a-z]?))"
example = "https://ww2.mangafreak.me/Read1_Onepunch_Man_1"
def __init__(self, match):
ChapterExtractor.__init__(self, match, self.root + match.group(1))
self.manga_slug, self.chapter = match.groups()[1:]
def metadata(self, page):
extr = text.extract_from(page)
manga = text.unescape(extr("<title>", " Chapter "))
title = text.unescape(extr("", " - MangaFreak"))
chapter_str = extr("# ", " MANGA ONLINE")
# Parse chapter number and minor suffix (e.g., "167e" -> chapter=167, minor="e")
chapter, sep, minor = self.chapter.partition("e") if "e" in self.chapter else (self.chapter, "", "")
chapter_str = self.groups[2]
chapter, sep, minor = chapter_str.partition("e")
return {
"manga" : manga,
"title" : title,
"chapter" : text.parse_int(chapter),
"chapter_minor": sep + minor,
"chapter_string": self.chapter,
"manga_slug" : self.manga_slug,
"chapter_string": chapter_str,
"manga_slug" : self.groups[1],
"lang" : "en",
"language" : "English",
}
def images(self, page):
# Extract all <img> tags pointing to manga images
return [
(url, None)
for url in text.extract_iter(page, '<img src="https://images.mangafreak.me/mangas/', '"')
("https://images.mangafreak.me/mangas/" + path, None)
for path in text.extract_iter(
page, 'src="https://images.mangafreak.me/mangas/', '"')
]
@@ -63,54 +58,35 @@ class MangafreakMangaExtractor(MangafreakBase, MangaExtractor):
pattern = BASE_PATTERN + r"(/Manga/([^/?#]+))"
example = "https://ww2.mangafreak.me/Manga/Onepunch_Man"
def __init__(self, match):
MangaExtractor.__init__(self, match, self.root + match.group(1))
self.manga_slug = match.group(2)
def chapters(self, page):
extr = text.extract_from(page)
manga = text.unescape(extr("<title>", " Manga"))
# Extract chapter list from table
chapter_list = text.extr(page, "<tbody>", "</tbody>")
if not chapter_list:
chapter_table = text.extr(page, "<table>", "</table>")
if not chapter_table:
return []
data = {
"manga" : manga,
"manga_slug" : self.manga_slug,
"lang" : "en",
"language" : "English",
"manga" : manga,
"manga_slug": self.groups[1],
"lang" : "en",
"language" : "English",
}
results = []
for row in text.extract_iter(chapter_list, "<tr>", "</tr>"):
# Extract chapter link and date from each row
chapter_link = text.extr(row, '<a href="', '"')
if not chapter_link:
for row in text.extract_iter(chapter_table, "<tr>", "</tr>"):
href = text.extr(row, '<a href="', '"')
if not href:
continue
url = self.root + href
chapter_str = url.rpartition("_")[2]
chapter, sep, minor = chapter_str.partition("e")
# Build full URL if relative
if chapter_link.startswith("/"):
url = self.root + chapter_link
else:
url = self.root + "/" + chapter_link
# Parse chapter info from URL like /Read1_Onepunch_Man_167e
chapter_part = url.rsplit("/", 1)[-1] # Read1_Onepunch_Man_167e
if chapter_part.startswith("Read1_"):
parts = chapter_part.split("_")
if len(parts) >= 3:
chapter_str = parts[-1]
# Parse chapter number and minor suffix
chapter, sep, minor = chapter_str.partition("e") if "e" in chapter_str else (chapter_str, "", "")
chapter_data = {
"chapter" : text.parse_int(chapter),
"chapter_minor": sep + minor,
"chapter_string": chapter_str,
**data,
}
results.append((url, chapter_data))
results.append((url, {
"chapter" : text.parse_int(chapter),
"chapter_minor": sep + minor,
"chapter_string": chapter_str,
**data,
}))
return results