dahjah/grawlix
1
0
Fork 0
mirror of https://github.com/jo1gi/grawlix.git synced 2026-06-05 05:54:56 -06:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update Internet Archive metadata retrieval

Browse Source 
Should fix issue 17
This commit is contained in:
Joakim Holm 2024-05-10 22:28:28 +02:00
parent f154be5c25
commit 465abbecad
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
grawlix/sources/internet_archive.py
View File

@ -1,10 +1,13 @@
from grawlix.book import Book, SingleFile, Metadata, OfflineFile from grawlix.book import Book, SingleFile, Metadata, OfflineFile
from grawlix.exceptions import DataNotFound
from grawlix import logging
from .source import Source from .source import Source
import random import random
import string import string
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
import asyncio import asyncio
import json
class InternetArchive(Source): class InternetArchive(Source):
name: str = "Internet Archive" name: str = "Internet Archive"
@ -104,8 +107,10 @@ class InternetArchive(Source):
f"https://archive.org/details/{book_id}" f"https://archive.org/details/{book_id}"
) )
soup = BeautifulSoup(page_response.text, "lxml") soup = BeautifulSoup(page_response.text, "lxml")
metadata_url = soup.find("ia-book-theater").get("bookmanifesturl") reader_data = json.loads(soup.find(class_="js-bookreader").get("value"))
metadata_url = f"https:{reader_data['url']}"
logging.debug(f"{metadata_url=}")
metadata_response = await self._client.get( metadata_response = await self._client.get(
f"https:{metadata_url}" metadata_url
) )
return metadata_response.json()["data"]["metadata"] return metadata_response.json()["data"]["metadata"]