markil3/ComicDownload
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Adds request header functionality and fixes indexing

Browse Source 
The headers are useful for working around 401 errors. The indexing changes prevent crashes from tuple identifiers.
This commit is contained in:
Markil 3
2025-08-12 13:12:00 -06:00
parent b204ae5508
commit b15913b4ca
1 changed files with 13 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
comic_download/comic_strip.py
View File

@@ -79,7 +79,7 @@ def get_identifier_string(identifier):
return identifier return identifier
elif type(identifier) == tuple or type(identifier) == list: elif type(identifier) == tuple or type(identifier) == list:
# Check for spaces. Their presence influenced the delimiter string. # Check for spaces. Their presence influenced the delimiter string.
if any(re.search(r'\s', id) for id in identifier): if any(re.search(r'\s', str(id)) for id in identifier):
delimiter = ' - ' delimiter = ' - '
else: else:
delimiter = '-' delimiter = '-'
@@ -100,6 +100,12 @@ class ImageRepo(ABC):
seperately. seperately.
""" """
download_headers = {
"accept-language": "en-US,en;q=0.9",
"dnt": "1",
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
def __init__(self, identifier, image_type): def __init__(self, identifier, image_type):
""" """
Creates an information repository Creates an information repository
@@ -249,7 +255,7 @@ class ImageRepo(ABC):
for name in iterator: for name in iterator:
logging.info(" Downloading repository %s resource %s", self.get_identifier_string(), name) logging.info(" Downloading repository %s resource %s", self.get_identifier_string(), name)
image_path = NamedTemporaryFile(mode='wb', suffix=str(name), prefix=self.get_identifier_string(), delete = False) image_path = NamedTemporaryFile(mode='wb', suffix=str(name), prefix=self.get_identifier_string(), delete = False)
result = requests.get(self.image_urls[name]) result = requests.get(self.image_urls[name], headers=self.download_headers)
result.raise_for_status() result.raise_for_status()
image_path.write(result.content) image_path.write(result.content)
image_path.close() image_path.close()
@@ -330,8 +336,8 @@ class Comic(ImageRepo, ABC):
""" """
with self._index_lock: with self._index_lock:
if not self.identifier in self.strip_index: if not self.identifier in self.strip_index:
self.strip_index[self.identifier] = {} self.strip_index[self.get_identifier_string()] = {}
self.strip_index[self.identifier][strip.identifier] = strip.get_filename() self.strip_index[self.get_identifier_string()][strip.identifier] = strip.get_filename()
def is_strip_present(self, base_path: Path, suffix: str, identifier) -> bool: def is_strip_present(self, base_path: Path, suffix: str, identifier) -> bool:
""" """
@@ -342,11 +348,11 @@ class Comic(ImageRepo, ABC):
:param identifier: The identifier to check. :param identifier: The identifier to check.
:returns: True if the strip file has been saved. :returns: True if the strip file has been saved.
""" """
if not self.identifier in self.strip_index: if not self.get_identifier_string() in self.strip_index:
return False return False
if not identifier in self.strip_index[self.identifier]: if not identifier in self.strip_index[self.get_identifier_string()]:
return False return False
path = Path(base_path, self.strip_index[self.identifier][identifier] + suffix) path = Path(base_path, self.strip_index[self.get_identifier_string()][identifier] + suffix)
return path.exists() return path.exists()