missytake/fetch-comic
1
0
Fork 0
Code Issues Pull requests Actions Packages Projects Releases Wiki Activity

feat: allow to specify the html attribute for --next & --img

Browse source
This commit is contained in:
missytake 2025-12-20 12:13:26 +01:00
parent e400554060
commit 3ea6392689
Signed by: missytake
GPG key ID: 04CC6658320518DF
1 changed files with 22 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

40
main.py
View file

@ -11,9 +11,9 @@ def fetch_page(
i: int,
url: str,
download: bool,
img_id: str,
img_tag: {str,str},
out_dir: Path,
next_rel: str,
next_tag: {str,str},
) -> str:
"""Download a comic from a URL and return the URL of the next page
@ -21,9 +21,9 @@ def fetch_page(
:param i: which page of the comic this is
:param url: the URL of the page
:param download: whether to download the comic
:param img_id: the id of the <img> tag where the comic is located
:param img_tag: the html attribute and its content of the <img> tag where the comic is located
:param out_dir: the directory the comic is saved to
:param next_rel: the tag of the "next" button
:param next_tag: the html attribute and its content of the "next" button
:return: the URL of the next page, None if it doesn't exist
"""
if not url.startswith("https://"):
@ -32,7 +32,7 @@ def fetch_page(
soup = BeautifulSoup(page.text, "html.parser")
if download:
img_url = soup.find("img", id=img_id).get("src")
img_url = soup.find("img", **img_tag).get("src")
if not img_url.startswith("https://"):
img_url = domain + img_url
comic = requests.get(img_url)
@ -46,7 +46,7 @@ def fetch_page(
output_file.write(comic.content)
output_file.close()
return soup.find("a", rel=next_rel).get("href")
return soup.find("a", **next_tag).get("href")
def fetch_comic(args):
@ -56,14 +56,18 @@ def fetch_comic(args):
out_dir = Path(os.getcwd()).joinpath(args.output)
next_rel = args.next
img_id = args.img
if not next_rel or not img_id:
for style in soup.find_all("link", rel="stylesheet"):
if style.get("href").endswith("/comiccontrol/defaultstyles.css"):
img_id = "cc-comic" if not args.img else args.img
next_rel = "next" if not args.next else args.next
break
for style in soup.find_all("link", rel="stylesheet"):
if style.get("href").endswith("/comiccontrol/defaultstyles.css"):
img_tag = {"id": "cc-comic"}
next_tag = {"rel": "next"}
break
if args.next:
next_split = args.next.split("::")
next_tag = {next_split[0]: next_split[1]}
if args.img:
img_split = args.img.split("::")
img_tag = {img_split[0]: img_split[1]}
if args.first:
first_url = soup.find("a", rel=args.first).get("href")
@ -73,7 +77,7 @@ def fetch_comic(args):
soup = BeautifulSoup(page.text, "html.parser")
try:
next_url = soup.find("a", rel=next_rel).get("href")
next_url = soup.find("a", **next_tag).get("href")
except AttributeError:
print(soup.find("a"))
i = 1
@ -82,7 +86,7 @@ def fetch_comic(args):
download = False if i < begin else True
print(f"Fetching: {next_url}")
next_url = fetch_page(
args.domain, i, next_url, download, img_id, out_dir, next_rel
args.domain, i, next_url, download, img_tag, out_dir, next_tag
)
if not next_url:
break # end reached
@ -101,13 +105,13 @@ def cli():
)
parser.add_argument(
"--img", default=None, help="html 'id' tag of the comic's img element(s)"
"--img", default=None, help="a unique html_attribute::content of the comic's img element"
)
parser.add_argument(
"--first", default=None, help="html 'rel' tag of the 'first comic' button"
)
parser.add_argument(
"--next", default=None, help="html 'rel' tag of the 'next comic' button"
"--next", default=None, help="html attribute and content of the 'next comic' button"
)
parser.add_argument(