gptc-news-model/download.py

108 lines
3.4 KiB
Python
Executable File

#!/usr/bin/env python3
# SPDX-License-Identifier: GPL-3.0-or-later
# Copyright (c) 2022 Samuel L Sloniker
#
# This program is free software: you can redistribute it and/or modify it under
# the terms of the GNU General Public License as published by the Free Software
# Foundation, either version 3 of the License, or (at your option) any later
# version.
#
# This program is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
# details.
#
# You should have received a copy of the GNU General Public License along with
# this program. If not, see <https://www.gnu.org/licenses/>.
import feedparser
import sqlite3
import goose3
import tomli
import bs4
def matches(string, checks):
for check in checks:
if check["type"] == "startswith" and string.startswith(
check["pattern"]
):
return True
return False
with open("sources.toml", "rb") as f:
sources = tomli.load(f)
g = goose3.Goose()
con = sqlite3.connect("articles.db")
con.execute("CREATE TABLE IF NOT EXISTS articles(source, category, url, text);")
known = [i[0] for i in con.execute("SELECT url FROM articles;")]
try:
for (url,) in con.execute("SELECT url FROM articles WHERE (text = '***');"):
print(f"Downloading {url}...")
con.execute(
"UPDATE articles SET text = ? WHERE (url = ?);",
(
g.extract(url).cleaned_text,
url,
),
)
print("Done downloading.")
for name, config in sources.items():
url = config["feed"]
category = config["category"]
contains_articles = config["contains_articles"]
print(f"Fetching {name} feed ({url})...")
entries = [
entry
for entry in feedparser.parse(url)["entries"]
if not entry["link"] in known
and not matches(entry["link"], config.get("exclude", []))
]
print(f"Fetched feed. Found {len(entries)} new articles.")
if contains_articles:
for entry in entries:
try:
print(f"Saving {entry['link']}")
con.execute(
"INSERT INTO articles VALUES (?, ?, ?, ?);",
(
name,
category,
entry["link"],
bs4.BeautifulSoup(
entry["content"][0]["value"], features="lxml"
).text,
),
)
except KeyError:
print("Not enough information. Skipping.")
else:
for entry in entries:
try:
print(f"Downloading {entry['link']}...")
con.execute(
"INSERT INTO articles VALUES (?, ?, ?, ?);",
(
name,
category,
entry["link"],
g.extract(entry["link"]).cleaned_text,
),
)
print(f"Done downloading.")
except KeyError:
print("Not enough information. Skipping.")
finally:
con.commit()
con.close()