inoreader2readwise/main.py

122 lines
4.0 KiB
Python

import os
import time
import json
import requests
import logging
# Define the path to the persistent data store
DATA_STORE_PATH = "/data/last_update_time.txt"
# Set up logging
logging.basicConfig(level=logging.INFO)
class APIHandler:
def __init__(self, base_url, headers={}):
self.base_url = base_url
self.headers = headers
def get(self, endpoint, params=None):
response = requests.get(self.base_url + endpoint, params=params, headers=self.headers)
response.raise_for_status()
return response.json()
def post(self, endpoint, data=None):
response = requests.post(self.base_url + endpoint, data=json.dumps(data), headers=self.headers)
response.raise_for_status()
return response.status_code
def get_last_update_time():
with open(DATA_STORE_PATH, 'r') as file:
return file.read().strip()
def update_last_update_time(new_time):
with open(DATA_STORE_PATH, 'w') as file:
file.write(new_time)
def main():
# Get credentials from environment variables
inoreader = APIHandler(
"https://www.inoreader.com/reader/api/0/stream/contents",
headers = {
'Authorization': 'Bearer ' + os.getenv("INOREADER_ACCESS_TOKEN")
})
readwise = APIHandler(
"https://readwise.io",
headers = {
'Authorization': 'Token ' + os.getenv("READWISE_ACCESS_TOKEN"),
'Content-Type': 'application/json'
}
)
while True:
try:
last_annotation_time = get_last_update_time()
# Get annotations after the last update time
inoreader_response = inoreader.get(
"/user/-/state/com.google/annotated",
params={
"annotations": 1,
"n": 100,
#"ot": last_annotation_time or None
}
)
data = json.loads(inoreader_response)
all_annotations = []
for item in data["items"]:
annotations = item.get("annotations", [])
all_annotations.extend(annotations)
# Filter annotations
new_annotations = [annotation for annotation in all_annotations if annotation['added_on'] > last_annotation_time]
if new_annotations:
latest_added_on = max(annotation['added_on'] for annotation in new_annotations)
else:
latest_added_on = None
# group annotations by title and author
grouped_annotations = {}
for annotation in new_annotations:
title = annotation['title']
author = annotation['author']
key = (title, author)
if key not in grouped_annotations:
grouped_annotations[key] = []
grouped_annotations[key].append(annotation)
# Push annotations to Readwise
readwise.post(
"/api/v2/highlights/",
# convert the grouped_annotations above for readwise payload
data={
'highlights': [
{
'text': annotation['text'],
'title': key[0],
'author': key[1],
'note': annotation['note'],
}
for key, annotations in grouped_annotations.items()
for annotation in annotations
]
}
)
# Update the last annotation time
if latest_added_on:
update_last_update_time(latest_added_on)
else:
logging.info("No new annotations found")
# Wait for an hour
time.sleep(3600)
except Exception as e:
logging.error(f"An error occurred: {e}")
time.sleep(60) # Wait a minute before retrying
if __name__ == "__main__":
main()