dahjah/grawlix
1
0
Fork 0
mirror of https://github.com/jo1gi/grawlix.git synced 2025-12-16 04:09:10 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Make onlinefiles support cookies

Browse Source
This commit is contained in:
Joakim Holm 2023-06-01 22:32:04 +02:00
parent 2faa4b747b
commit dade9db6da
3 changed files with 15 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
grawlix/book.py
View File

@ -1,6 +1,6 @@
from grawlix import Encryption from grawlix import Encryption
from dataclasses import dataclass, field from dataclasses import dataclass, field
from typing import Optional, Union, TypeVar, Generic from typing import Optional, Union, TypeVar, Generic, Any
@dataclass(slots=True) @dataclass(slots=True)
class Metadata: class Metadata:
@ -30,6 +30,7 @@ class OnlineFile:
extension: str extension: str
encryption: Optional[Encryption] = None encryption: Optional[Encryption] = None
headers: Optional[dict[str, str]] = None headers: Optional[dict[str, str]] = None
cookies: Optional[Any] = None # TODO Change type
@dataclass(slots=True) @dataclass(slots=True)
class OfflineFile: class OfflineFile:
@ -63,8 +64,8 @@ class HtmlFile:
@dataclass(slots=True) @dataclass(slots=True)
class HtmlFiles: class HtmlFiles:
cover: OnlineFile
htmlfiles: list[HtmlFile] htmlfiles: list[HtmlFile]
cover: Optional[OnlineFile] = None
BookData = Union[ BookData = Union[
SingleFile, SingleFile,

15
grawlix/output/epub.py
View File

@ -27,9 +27,9 @@ class Epub(OutputFormat):
file_count = len(html.htmlfiles) + 1 # Html files + cover file_count = len(html.htmlfiles) + 1 # Html files + cover
async def download_cover(cover_file: OnlineFile): async def download_cover(cover_file: OnlineFile):
cover_filename = f"cover.{html.cover.extension}" cover_filename = f"cover.{cover_file.extension}"
epub_cover = epub.EpubCover(file_name = cover_filename) epub_cover = epub.EpubCover(file_name = cover_filename)
epub_cover.content = await self._download_file(html.cover) epub_cover.content = await self._download_file(cover_file)
output.add_item(epub_cover) output.add_item(epub_cover)
epub_cover_page = epub.EpubCoverHtml(image_name = cover_filename) epub_cover_page = epub.EpubCoverHtml(image_name = cover_filename)
if update: if update:
@ -38,7 +38,12 @@ class Epub(OutputFormat):
async def download_file(index: int, file: HtmlFile): async def download_file(index: int, file: HtmlFile):
response = await self._client.get(file.file.url, follow_redirects=True) response = await self._client.get(
file.file.url,
headers = file.file.headers,
cookies = file.file.cookies,
follow_redirects=True
)
soup = BeautifulSoup(response.text, "lxml") soup = BeautifulSoup(response.text, "lxml")
selected_element = soup.find(attrs=file.selector) selected_element = soup.find(attrs=file.selector)
epub_file = epub.EpubHtml( epub_file = epub.EpubHtml(
@ -55,7 +60,9 @@ class Epub(OutputFormat):
download_file(index, file) download_file(index, file)
for index, file in enumerate(html.htmlfiles) for index, file in enumerate(html.htmlfiles)
] ]
epub_files = await asyncio.gather(download_cover(html.cover), *tasks) if html.cover:
tasks.append(download_cover(html.cover))
epub_files = await asyncio.gather(*tasks)
# Add files to epub # Add files to epub
for epub_file in epub_files: for epub_file in epub_files:

2
grawlix/output/output_format.py
View File

@ -59,7 +59,7 @@ class OutputFormat:
:returns: Content of downloaded file :returns: Content of downloaded file
""" """
content = b"" content = b""
async with self._client.stream("GET", file.url, headers = file.headers, follow_redirects=True) as request: async with self._client.stream("GET", file.url, headers = file.headers, cookies = file.cookies, follow_redirects=True) as request:
total_filesize = int(request.headers["Content-length"]) total_filesize = int(request.headers["Content-length"])
async for chunk in request.aiter_bytes(): async for chunk in request.aiter_bytes():
content += chunk content += chunk