2024-01-04 02:16:24 +01:00
|
|
|
#!/usr/bin/env python3
|
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
2024-01-06 23:03:08 +01:00
|
|
|
"""
|
|
|
|
|
|
|
|
TODO
|
|
|
|
|
|
|
|
1) Call sqlite function from function statistics.
|
|
|
|
Returning a list of values doesn't' seem to be a good practice.
|
|
|
|
|
|
|
|
"""
|
|
|
|
|
2024-01-04 02:16:24 +01:00
|
|
|
from asyncio.exceptions import IncompleteReadError
|
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
from http.client import IncompleteRead
|
|
|
|
from feedparser import parse
|
2024-01-06 23:03:08 +01:00
|
|
|
import logging
|
2024-01-04 02:16:24 +01:00
|
|
|
import slixfeed.config as config
|
|
|
|
import slixfeed.crawl as crawl
|
2024-01-06 23:03:08 +01:00
|
|
|
from slixfeed.datetime import (
|
|
|
|
current_date, current_time, now,
|
|
|
|
convert_struct_time_to_iso8601,
|
|
|
|
rfc2822_to_iso8601
|
|
|
|
)
|
2024-01-04 02:16:24 +01:00
|
|
|
import slixfeed.fetch as fetch
|
|
|
|
import slixfeed.sqlite as sqlite
|
2024-01-06 23:03:08 +01:00
|
|
|
from slixfeed.url import (
|
|
|
|
# complete_url,
|
|
|
|
join_url,
|
|
|
|
remove_tracking_parameters,
|
|
|
|
replace_hostname,
|
|
|
|
trim_url
|
|
|
|
)
|
|
|
|
import slixfeed.xmpp.bookmark as bookmark
|
2024-01-04 02:16:24 +01:00
|
|
|
from urllib import error
|
|
|
|
from urllib.parse import urlsplit
|
2024-01-06 23:03:08 +01:00
|
|
|
import xml.etree.ElementTree as ET
|
|
|
|
|
|
|
|
|
|
|
|
def log_to_markdown(timestamp, filename, jid, message):
|
|
|
|
"""
|
|
|
|
Log message to file.
|
|
|
|
|
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
timestamp : str
|
|
|
|
Time stamp.
|
|
|
|
filename : str
|
|
|
|
Jabber ID as name of file.
|
|
|
|
jid : str
|
|
|
|
Jabber ID.
|
|
|
|
message : str
|
|
|
|
Message content.
|
|
|
|
|
|
|
|
Returns
|
|
|
|
-------
|
|
|
|
None.
|
|
|
|
|
|
|
|
"""
|
|
|
|
with open(filename + '.md', 'a') as file:
|
|
|
|
# entry = "{} {}:\n{}\n\n".format(timestamp, jid, message)
|
|
|
|
entry = (
|
|
|
|
"## {}\n"
|
|
|
|
"### {}\n\n"
|
|
|
|
"{}\n\n").format(jid, timestamp, message)
|
|
|
|
file.write(entry)
|
|
|
|
|
|
|
|
|
|
|
|
def is_feed(feed):
|
|
|
|
"""
|
|
|
|
Determine whether document is feed or not.
|
|
|
|
|
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
feed : dict
|
|
|
|
Parsed feed.
|
|
|
|
|
|
|
|
Returns
|
|
|
|
-------
|
|
|
|
val : boolean
|
|
|
|
True or False.
|
|
|
|
"""
|
|
|
|
print("Check function action.is_feed")
|
|
|
|
breakpoint()
|
|
|
|
value = False
|
|
|
|
message = None
|
|
|
|
if not feed.entries:
|
|
|
|
if "version" in feed.keys():
|
|
|
|
feed["version"]
|
|
|
|
if feed.version:
|
|
|
|
value = True
|
|
|
|
# message = (
|
|
|
|
# "Empty feed for {}"
|
|
|
|
# ).format(url)
|
|
|
|
elif "title" in feed["feed"].keys():
|
|
|
|
value = True
|
|
|
|
# message = (
|
|
|
|
# "Empty feed for {}"
|
|
|
|
# ).format(url)
|
|
|
|
else:
|
|
|
|
value = False
|
|
|
|
# message = (
|
|
|
|
# "No entries nor title for {}"
|
|
|
|
# ).format(url)
|
|
|
|
elif feed.bozo:
|
|
|
|
value = False
|
|
|
|
# message = (
|
|
|
|
# "Bozo detected for {}"
|
|
|
|
# ).format(url)
|
|
|
|
else:
|
|
|
|
value = True
|
|
|
|
# message = (
|
|
|
|
# "Good feed for {}"
|
|
|
|
# ).format(url)
|
|
|
|
print(message)
|
|
|
|
return value
|
|
|
|
|
|
|
|
|
|
|
|
def list_unread_entries(result, feed_title):
|
|
|
|
# TODO Add filtering
|
|
|
|
# TODO Do this when entry is added to list and mark it as read
|
|
|
|
# DONE!
|
|
|
|
# results = []
|
|
|
|
# if get_settings_value(db_file, "filter-deny"):
|
|
|
|
# while len(results) < num:
|
|
|
|
# result = cur.execute(sql).fetchone()
|
|
|
|
# blacklist = await get_settings_value(db_file, "filter-deny").split(",")
|
|
|
|
# for i in blacklist:
|
|
|
|
# if i in result[1]:
|
|
|
|
# continue
|
|
|
|
# print("rejected:", result[1])
|
|
|
|
# print("accepted:", result[1])
|
|
|
|
# results.extend([result])
|
|
|
|
|
|
|
|
# news_list = "You've got {} news items:\n".format(num)
|
|
|
|
# NOTE Why doesn't this work without list?
|
|
|
|
# i.e. for result in results
|
|
|
|
# for result in results.fetchall():
|
|
|
|
ix = result[0]
|
|
|
|
title = result[1]
|
|
|
|
# # TODO Retrieve summary from feed
|
|
|
|
# # See fetch.view_entry
|
|
|
|
# summary = result[2]
|
|
|
|
# # Remove HTML tags
|
|
|
|
# try:
|
|
|
|
# summary = BeautifulSoup(summary, "lxml").text
|
|
|
|
# except:
|
|
|
|
# print(result[2])
|
|
|
|
# breakpoint()
|
|
|
|
# # TODO Limit text length
|
|
|
|
# summary = summary.replace("\n\n\n", "\n\n")
|
|
|
|
# length = await get_settings_value(db_file, "length")
|
|
|
|
# summary = summary[:length] + " […]"
|
|
|
|
# summary = summary.strip().split('\n')
|
|
|
|
# summary = ["> " + line for line in summary]
|
|
|
|
# summary = "\n".join(summary)
|
|
|
|
link = result[2]
|
|
|
|
link = remove_tracking_parameters(link)
|
|
|
|
link = (replace_hostname(link, "link")) or link
|
|
|
|
news_item = (
|
|
|
|
"\n{}\n{}\n{}\n"
|
|
|
|
).format(str(title), str(link), str(feed_title))
|
|
|
|
return news_item
|
|
|
|
|
|
|
|
|
|
|
|
def list_search_results(query, results):
|
|
|
|
results_list = (
|
|
|
|
"Search results for '{}':\n\n```"
|
|
|
|
).format(query)
|
|
|
|
for result in results:
|
|
|
|
results_list += (
|
|
|
|
"\n{}\n{}\n"
|
|
|
|
).format(str(result[0]), str(result[1]))
|
|
|
|
if len(results):
|
|
|
|
return results_list + "```\nTotal of {} results".format(len(results))
|
|
|
|
else:
|
|
|
|
return "No results were found for: {}".format(query)
|
|
|
|
|
|
|
|
|
|
|
|
def list_feeds_by_query(query, results):
|
|
|
|
results_list = (
|
|
|
|
"Feeds containing '{}':\n\n```"
|
|
|
|
).format(query)
|
|
|
|
for result in results:
|
|
|
|
results_list += (
|
|
|
|
"\nName : {} [{}]"
|
|
|
|
"\nURL : {}"
|
|
|
|
"\n"
|
|
|
|
).format(
|
|
|
|
str(result[0]), str(result[1]), str(result[2]))
|
|
|
|
if len(results):
|
|
|
|
return results_list + "\n```\nTotal of {} feeds".format(len(results))
|
|
|
|
else:
|
|
|
|
return "No feeds were found for: {}".format(query)
|
|
|
|
|
|
|
|
|
|
|
|
def list_statistics(values):
|
|
|
|
"""
|
|
|
|
Return table statistics.
|
|
|
|
|
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
db_file : str
|
|
|
|
Path to database file.
|
|
|
|
|
|
|
|
Returns
|
|
|
|
-------
|
|
|
|
msg : str
|
|
|
|
Statistics as message.
|
|
|
|
"""
|
|
|
|
msg = (
|
|
|
|
"```"
|
|
|
|
"\nSTATISTICS\n"
|
|
|
|
"News items : {}/{}\n"
|
|
|
|
"News sources : {}/{}\n"
|
|
|
|
"\nOPTIONS\n"
|
|
|
|
"Items to archive : {}\n"
|
|
|
|
"Update interval : {}\n"
|
|
|
|
"Items per update : {}\n"
|
|
|
|
"Operation status : {}\n"
|
|
|
|
"```"
|
|
|
|
).format(values[0], values[1], values[2], values[3],
|
|
|
|
values[4], values[5], values[6], values[7])
|
|
|
|
return msg
|
|
|
|
|
|
|
|
|
|
|
|
# FIXME Replace counter by len
|
|
|
|
def list_last_entries(results, num):
|
|
|
|
titles_list = "Recent {} titles:\n\n```".format(num)
|
|
|
|
for result in results:
|
|
|
|
titles_list += (
|
|
|
|
"\n{}\n{}\n"
|
|
|
|
).format(
|
|
|
|
str(result[0]), str(result[1]))
|
|
|
|
if len(results):
|
|
|
|
titles_list += "```\n"
|
|
|
|
return titles_list
|
|
|
|
else:
|
|
|
|
return "There are no news at the moment."
|
|
|
|
|
|
|
|
|
|
|
|
def list_feeds(results):
|
|
|
|
feeds_list = "\nList of subscriptions:\n\n```\n"
|
|
|
|
for result in results:
|
|
|
|
feeds_list += (
|
|
|
|
"Name : {}\n"
|
|
|
|
"URL : {}\n"
|
|
|
|
# "Updated : {}\n"
|
|
|
|
# "Status : {}\n"
|
|
|
|
"ID : {}\n"
|
|
|
|
"\n"
|
|
|
|
).format(
|
|
|
|
str(result[0]), str(result[1]), str(result[2]))
|
|
|
|
if len(results):
|
|
|
|
return feeds_list + (
|
|
|
|
"```\nTotal of {} subscriptions.\n"
|
|
|
|
).format(len(results))
|
|
|
|
else:
|
|
|
|
msg = (
|
|
|
|
"List of subscriptions is empty.\n"
|
|
|
|
"To add feed, send a URL\n"
|
|
|
|
"Try these:\n"
|
|
|
|
# TODO Pick random from featured/recommended
|
|
|
|
"https://reclaimthenet.org/feed/"
|
|
|
|
)
|
|
|
|
return msg
|
|
|
|
|
|
|
|
|
|
|
|
async def list_bookmarks(self):
|
|
|
|
conferences = await bookmark.get(self)
|
|
|
|
groupchat_list = "\nList of groupchats:\n\n```\n"
|
|
|
|
counter = 0
|
|
|
|
for conference in conferences:
|
|
|
|
counter += 1
|
|
|
|
groupchat_list += (
|
|
|
|
"{}\n"
|
|
|
|
"\n"
|
|
|
|
).format(
|
|
|
|
conference["jid"]
|
|
|
|
)
|
|
|
|
groupchat_list += (
|
|
|
|
"```\nTotal of {} groupchats.\n"
|
|
|
|
).format(counter)
|
|
|
|
return groupchat_list
|
|
|
|
|
|
|
|
|
|
|
|
def export_to_markdown(jid, filename, results):
|
|
|
|
with open(filename, 'w') as file:
|
|
|
|
file.write(
|
|
|
|
'# Subscriptions for {}\n'.format(jid))
|
|
|
|
file.write(
|
|
|
|
'## Set of feeds exported with Slixfeed\n')
|
|
|
|
for result in results:
|
|
|
|
file.write(
|
|
|
|
'- [{}]({})\n'.format(result[0], result[1]))
|
|
|
|
file.write(
|
|
|
|
'\n\n* * *\n\nThis list was saved on {} from xmpp:{} using '
|
|
|
|
'[Slixfeed](https://gitgud.io/sjehuda/slixfeed)\n'.format(
|
|
|
|
current_date(), jid))
|
|
|
|
|
|
|
|
|
|
|
|
def export_to_opml(jid, filename, results):
|
|
|
|
root = ET.Element("opml")
|
|
|
|
root.set("version", "1.0")
|
|
|
|
head = ET.SubElement(root, "head")
|
|
|
|
ET.SubElement(head, "title").text = "Subscriptions for {}".format(jid)
|
|
|
|
ET.SubElement(head, "description").text = (
|
|
|
|
"Set of feeds exported with Slixfeed")
|
|
|
|
ET.SubElement(head, "generator").text = "Slixfeed"
|
|
|
|
ET.SubElement(head, "urlPublic").text = (
|
|
|
|
"https://gitgud.io/sjehuda/slixfeed")
|
|
|
|
time_stamp = current_time()
|
|
|
|
ET.SubElement(head, "dateCreated").text = time_stamp
|
|
|
|
ET.SubElement(head, "dateModified").text = time_stamp
|
|
|
|
body = ET.SubElement(root, "body")
|
|
|
|
for result in results:
|
|
|
|
outline = ET.SubElement(body, "outline")
|
|
|
|
outline.set("text", result[0])
|
|
|
|
outline.set("xmlUrl", result[1])
|
|
|
|
# outline.set("type", result[2])
|
|
|
|
tree = ET.ElementTree(root)
|
|
|
|
tree.write(filename)
|
|
|
|
|
|
|
|
|
|
|
|
async def import_opml(db_file, url):
|
|
|
|
result = await fetch.download_feed(url)
|
|
|
|
document = result[0]
|
|
|
|
if document:
|
|
|
|
root = ET.fromstring(document)
|
|
|
|
before = await sqlite.get_number_of_items(
|
|
|
|
db_file, 'feeds')
|
|
|
|
feeds = []
|
|
|
|
for child in root.findall(".//outline"):
|
|
|
|
url = child.get("xmlUrl")
|
|
|
|
title = child.get("text")
|
|
|
|
# feed = (url, title)
|
|
|
|
# feeds.extend([feed])
|
|
|
|
feeds.extend([(url, title)])
|
|
|
|
await sqlite.import_feeds(
|
|
|
|
db_file, feeds)
|
|
|
|
after = await sqlite.get_number_of_items(
|
|
|
|
db_file, 'feeds')
|
|
|
|
difference = int(after) - int(before)
|
|
|
|
return difference
|
2024-01-04 02:16:24 +01:00
|
|
|
|
|
|
|
|
|
|
|
async def add_feed(db_file, url):
|
|
|
|
while True:
|
2024-01-06 23:03:08 +01:00
|
|
|
exist = await sqlite.get_feed_id_and_name(db_file, url)
|
2024-01-04 02:16:24 +01:00
|
|
|
if not exist:
|
2024-01-04 14:58:06 +01:00
|
|
|
result = await fetch.download_feed(url)
|
2024-01-04 02:16:24 +01:00
|
|
|
document = result[0]
|
2024-01-06 23:03:08 +01:00
|
|
|
status_code = result[1]
|
2024-01-04 02:16:24 +01:00
|
|
|
if document:
|
|
|
|
feed = parse(document)
|
2024-01-06 23:03:08 +01:00
|
|
|
# if is_feed(url, feed):
|
|
|
|
if is_feed(feed):
|
|
|
|
if "title" in feed["feed"].keys():
|
2024-01-04 02:16:24 +01:00
|
|
|
title = feed["feed"]["title"]
|
2024-01-06 23:03:08 +01:00
|
|
|
else:
|
2024-01-04 02:16:24 +01:00
|
|
|
title = urlsplit(url).netloc
|
2024-01-06 23:03:08 +01:00
|
|
|
if "language" in feed["feed"].keys():
|
|
|
|
language = feed["feed"]["language"]
|
|
|
|
else:
|
|
|
|
language = ''
|
|
|
|
if "encoding" in feed.keys():
|
|
|
|
encoding = feed["encoding"]
|
|
|
|
else:
|
|
|
|
encoding = ''
|
|
|
|
if "updated_parsed" in feed["feed"].keys():
|
|
|
|
updated = feed["feed"]["updated_parsed"]
|
|
|
|
updated = convert_struct_time_to_iso8601(updated)
|
|
|
|
else:
|
|
|
|
updated = ''
|
|
|
|
version = feed["version"]
|
|
|
|
entries = len(feed["entries"])
|
2024-01-04 02:16:24 +01:00
|
|
|
await sqlite.insert_feed(
|
2024-01-06 23:03:08 +01:00
|
|
|
db_file, url,
|
|
|
|
title=title,
|
|
|
|
entries=entries,
|
|
|
|
version=version,
|
|
|
|
encoding=encoding,
|
|
|
|
language=language,
|
|
|
|
status_code=status_code,
|
|
|
|
updated=updated
|
|
|
|
)
|
|
|
|
await scan(
|
|
|
|
db_file, url)
|
2024-01-04 13:38:22 +01:00
|
|
|
old = (
|
|
|
|
await sqlite.get_settings_value(
|
|
|
|
db_file, "old")
|
|
|
|
) or (
|
|
|
|
config.get_value_default(
|
|
|
|
"settings", "Settings", "old")
|
|
|
|
)
|
2024-01-04 02:16:24 +01:00
|
|
|
if not old:
|
2024-01-06 23:03:08 +01:00
|
|
|
await sqlite.mark_feed_as_read(
|
2024-01-04 02:16:24 +01:00
|
|
|
db_file, url)
|
|
|
|
response = (
|
|
|
|
"> {}\nNews source {} has been "
|
|
|
|
"added to subscription list."
|
|
|
|
).format(url, title)
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
result = await crawl.probe_page(
|
|
|
|
url, document)
|
|
|
|
# TODO Check length and for a write a
|
|
|
|
# unified message for a set of feeds.
|
|
|
|
# Use logging if you so choose to
|
|
|
|
# distinct the methods
|
|
|
|
if isinstance(result, list):
|
|
|
|
url = result[0]
|
|
|
|
elif isinstance(result, str):
|
|
|
|
response = result
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
response = (
|
|
|
|
"> {}\nFailed to load URL. Reason: {}"
|
2024-01-06 23:03:08 +01:00
|
|
|
).format(url, status_code)
|
2024-01-04 02:16:24 +01:00
|
|
|
break
|
|
|
|
else:
|
|
|
|
ix = exist[0]
|
|
|
|
name = exist[1]
|
|
|
|
response = (
|
|
|
|
"> {}\nNews source \"{}\" is already "
|
|
|
|
"listed in the subscription list at "
|
|
|
|
"index {}".format(url, name, ix)
|
|
|
|
)
|
|
|
|
break
|
|
|
|
return response
|
|
|
|
|
|
|
|
|
|
|
|
async def view_feed(url):
|
|
|
|
while True:
|
2024-01-04 14:58:06 +01:00
|
|
|
result = await fetch.download_feed(url)
|
2024-01-04 02:16:24 +01:00
|
|
|
document = result[0]
|
|
|
|
status = result[1]
|
|
|
|
if document:
|
|
|
|
feed = parse(document)
|
2024-01-06 23:03:08 +01:00
|
|
|
# if is_feed(url, feed):
|
|
|
|
if is_feed(feed):
|
|
|
|
if "title" in feed["feed"].keys():
|
2024-01-04 02:16:24 +01:00
|
|
|
title = feed["feed"]["title"]
|
2024-01-06 23:03:08 +01:00
|
|
|
else:
|
2024-01-04 02:16:24 +01:00
|
|
|
title = urlsplit(url).netloc
|
|
|
|
entries = feed.entries
|
|
|
|
response = "Preview of {}:\n\n```\n".format(title)
|
|
|
|
counter = 0
|
|
|
|
for entry in entries:
|
|
|
|
counter += 1
|
|
|
|
if entry.has_key("title"):
|
|
|
|
title = entry.title
|
|
|
|
else:
|
|
|
|
title = "*** No title ***"
|
|
|
|
if entry.has_key("link"):
|
|
|
|
# link = complete_url(source, entry.link)
|
|
|
|
link = join_url(url, entry.link)
|
|
|
|
link = trim_url(link)
|
|
|
|
else:
|
|
|
|
link = "*** No link ***"
|
|
|
|
if entry.has_key("published"):
|
|
|
|
date = entry.published
|
|
|
|
date = rfc2822_to_iso8601(date)
|
|
|
|
elif entry.has_key("updated"):
|
|
|
|
date = entry.updated
|
|
|
|
date = rfc2822_to_iso8601(date)
|
|
|
|
else:
|
|
|
|
date = "*** No date ***"
|
|
|
|
response += (
|
|
|
|
"Title : {}\n"
|
|
|
|
"Date : {}\n"
|
|
|
|
"Link : {}\n"
|
|
|
|
"Count : {}\n"
|
|
|
|
"\n"
|
|
|
|
).format(title, date, link, counter)
|
|
|
|
if counter > 4:
|
|
|
|
break
|
|
|
|
response += (
|
|
|
|
"```\nSource: {}"
|
|
|
|
).format(url)
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
result = await crawl.probe_page(
|
|
|
|
url, document)
|
|
|
|
# TODO Check length and for a write a
|
|
|
|
# unified message for a set of feeds.
|
|
|
|
# Use logging if you so choose to
|
|
|
|
# distinct the methods
|
|
|
|
if isinstance(result, list):
|
|
|
|
url = result[0]
|
|
|
|
elif isinstance(result, str):
|
|
|
|
response = result
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
response = (
|
|
|
|
"> {}\nFailed to load URL. Reason: {}"
|
|
|
|
).format(url, status)
|
|
|
|
break
|
|
|
|
return response
|
|
|
|
|
|
|
|
|
|
|
|
async def view_entry(url, num):
|
|
|
|
while True:
|
2024-01-04 14:58:06 +01:00
|
|
|
result = await fetch.download_feed(url)
|
2024-01-04 02:16:24 +01:00
|
|
|
document = result[0]
|
|
|
|
status = result[1]
|
|
|
|
if document:
|
|
|
|
feed = parse(document)
|
2024-01-06 23:03:08 +01:00
|
|
|
# if is_feed(url, feed):
|
|
|
|
if is_feed(feed):
|
|
|
|
if "title" in feed["feed"].keys():
|
2024-01-04 02:16:24 +01:00
|
|
|
title = feed["feed"]["title"]
|
2024-01-06 23:03:08 +01:00
|
|
|
else:
|
2024-01-04 02:16:24 +01:00
|
|
|
title = urlsplit(url).netloc
|
|
|
|
entries = feed.entries
|
|
|
|
num = int(num) - 1
|
|
|
|
entry = entries[num]
|
|
|
|
response = "Preview of {}:\n\n```\n".format(title)
|
|
|
|
if entry.has_key("title"):
|
|
|
|
title = entry.title
|
|
|
|
else:
|
|
|
|
title = "*** No title ***"
|
|
|
|
if entry.has_key("published"):
|
|
|
|
date = entry.published
|
|
|
|
date = rfc2822_to_iso8601(date)
|
|
|
|
elif entry.has_key("updated"):
|
|
|
|
date = entry.updated
|
|
|
|
date = rfc2822_to_iso8601(date)
|
|
|
|
else:
|
|
|
|
date = "*** No date ***"
|
|
|
|
if entry.has_key("summary"):
|
|
|
|
summary = entry.summary
|
|
|
|
# Remove HTML tags
|
|
|
|
summary = BeautifulSoup(summary, "lxml").text
|
|
|
|
# TODO Limit text length
|
|
|
|
summary = summary.replace("\n\n\n", "\n\n")
|
|
|
|
else:
|
|
|
|
summary = "*** No summary ***"
|
|
|
|
if entry.has_key("link"):
|
|
|
|
# link = complete_url(source, entry.link)
|
|
|
|
link = join_url(url, entry.link)
|
|
|
|
link = trim_url(link)
|
|
|
|
else:
|
|
|
|
link = "*** No link ***"
|
|
|
|
response = (
|
|
|
|
"{}\n"
|
|
|
|
"\n"
|
|
|
|
# "> {}\n"
|
|
|
|
"{}\n"
|
|
|
|
"\n"
|
|
|
|
"{}\n"
|
|
|
|
"\n"
|
|
|
|
).format(title, summary, link)
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
result = await crawl.probe_page(
|
|
|
|
url, document)
|
|
|
|
# TODO Check length and for a write a
|
|
|
|
# unified message for a set of feeds.
|
|
|
|
# Use logging if you so choose to
|
|
|
|
# distinct the methods
|
|
|
|
if isinstance(result, list):
|
|
|
|
url = result[0]
|
|
|
|
elif isinstance(result, str):
|
|
|
|
response = result
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
response = (
|
|
|
|
"> {}\nFailed to load URL. Reason: {}"
|
|
|
|
).format(url, status)
|
|
|
|
break
|
|
|
|
return response
|
|
|
|
|
|
|
|
|
2024-01-06 23:03:08 +01:00
|
|
|
async def scan(db_file, url):
|
|
|
|
"""
|
|
|
|
Check feeds for new entries.
|
|
|
|
|
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
db_file : str
|
|
|
|
Path to database file.
|
|
|
|
url : str, optional
|
|
|
|
URL. The default is None.
|
|
|
|
"""
|
|
|
|
if isinstance(url, tuple): url = url[0]
|
|
|
|
try:
|
|
|
|
result = await fetch.download_feed(url)
|
|
|
|
except:
|
|
|
|
breakpoint()
|
|
|
|
# if not result:
|
|
|
|
# return
|
|
|
|
try:
|
|
|
|
document = result[0]
|
|
|
|
status = result[1]
|
|
|
|
except:
|
|
|
|
return
|
|
|
|
if document and status == 200:
|
|
|
|
feed = parse(document)
|
|
|
|
entries = feed.entries
|
|
|
|
# length = len(entries)
|
|
|
|
await remove_nonexistent_entries(
|
|
|
|
db_file, feed, url)
|
|
|
|
try:
|
|
|
|
if feed.bozo:
|
|
|
|
# bozo = (
|
|
|
|
# "WARNING: Bozo detected for feed: {}\n"
|
|
|
|
# "For more information, visit "
|
|
|
|
# "https://pythonhosted.org/feedparser/bozo.html"
|
|
|
|
# ).format(url)
|
|
|
|
# print(bozo)
|
|
|
|
valid = 0
|
|
|
|
else:
|
|
|
|
valid = 1
|
|
|
|
await sqlite.update_feed_validity(
|
|
|
|
db_file, url, valid)
|
|
|
|
if "updated_parsed" in feed["feed"].keys():
|
|
|
|
updated = feed["feed"]["updated_parsed"]
|
|
|
|
updated = convert_struct_time_to_iso8601(updated)
|
|
|
|
else:
|
|
|
|
updated = ''
|
|
|
|
await sqlite.update_feed_properties(
|
|
|
|
db_file, url, len(feed["entries"]), updated)
|
|
|
|
# await update_feed_status
|
|
|
|
except (
|
|
|
|
IncompleteReadError,
|
|
|
|
IncompleteRead,
|
|
|
|
error.URLError
|
|
|
|
) as e:
|
|
|
|
print("Error:", e)
|
|
|
|
return
|
|
|
|
# new_entry = 0
|
|
|
|
for entry in entries:
|
|
|
|
if entry.has_key("published"):
|
|
|
|
date = entry.published
|
|
|
|
date = rfc2822_to_iso8601(date)
|
|
|
|
elif entry.has_key("updated"):
|
|
|
|
date = entry.updated
|
|
|
|
date = rfc2822_to_iso8601(date)
|
|
|
|
else:
|
|
|
|
date = now()
|
|
|
|
if entry.has_key("link"):
|
|
|
|
# link = complete_url(source, entry.link)
|
|
|
|
link = join_url(url, entry.link)
|
|
|
|
link = trim_url(link)
|
|
|
|
else:
|
|
|
|
link = url
|
|
|
|
# title = feed["feed"]["title"]
|
|
|
|
# title = "{}: *{}*".format(feed["feed"]["title"], entry.title)
|
|
|
|
title = entry.title if entry.has_key("title") else date
|
|
|
|
entry_id = entry.id if entry.has_key("id") else link
|
|
|
|
summary = entry.summary if entry.has_key("summary") else ''
|
|
|
|
exist = await sqlite.check_entry_exist(
|
|
|
|
db_file, url, entry_id=entry_id,
|
|
|
|
title=title, link=link, date=date)
|
|
|
|
if not exist:
|
|
|
|
if entry.has_key("summary"):
|
|
|
|
summary = entry.summary
|
|
|
|
read_status = 0
|
|
|
|
pathname = urlsplit(link).path
|
|
|
|
string = ("{} {} {}"
|
|
|
|
).format(
|
|
|
|
title, summary, pathname
|
|
|
|
)
|
|
|
|
allow_list = await config.is_include_keyword(
|
|
|
|
db_file, "filter-allow", string)
|
|
|
|
if not allow_list:
|
|
|
|
reject_list = await config.is_include_keyword(
|
|
|
|
db_file, "filter-deny", string)
|
|
|
|
if reject_list:
|
|
|
|
read_status = 1
|
|
|
|
if isinstance(date, int):
|
|
|
|
logging.error("Variable 'date' is int:", date)
|
|
|
|
await sqlite.add_entry(
|
|
|
|
db_file, title, link, entry_id,
|
|
|
|
url, date, read_status)
|
|
|
|
await sqlite.set_date(db_file, url)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-04 02:16:24 +01:00
|
|
|
# NOTE Why (if res[0]) and (if res[1] == 200)?
|
|
|
|
async def organize_items(db_file, urls):
|
|
|
|
"""
|
|
|
|
Check feeds for new entries.
|
|
|
|
|
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
db_file : str
|
|
|
|
Path to database file.
|
|
|
|
url : str, optional
|
|
|
|
URL. The default is None.
|
|
|
|
"""
|
|
|
|
for url in urls:
|
|
|
|
# print(os.path.basename(db_file), url[0])
|
2024-01-06 23:03:08 +01:00
|
|
|
url = url[0]
|
|
|
|
res = await fetch.download_feed(url)
|
2024-01-04 02:16:24 +01:00
|
|
|
# TypeError: 'NoneType' object is not subscriptable
|
|
|
|
if res is None:
|
|
|
|
# Skip to next feed
|
|
|
|
# urls.next()
|
|
|
|
# next(urls)
|
|
|
|
continue
|
2024-01-06 23:03:08 +01:00
|
|
|
status = res[1]
|
|
|
|
await sqlite.update_feed_status(
|
|
|
|
db_file, url, status)
|
2024-01-04 02:16:24 +01:00
|
|
|
if res[0]:
|
|
|
|
try:
|
|
|
|
feed = parse(res[0])
|
|
|
|
if feed.bozo:
|
|
|
|
# bozo = (
|
|
|
|
# "WARNING: Bozo detected for feed: {}\n"
|
|
|
|
# "For more information, visit "
|
|
|
|
# "https://pythonhosted.org/feedparser/bozo.html"
|
2024-01-06 23:03:08 +01:00
|
|
|
# ).format(url)
|
2024-01-04 02:16:24 +01:00
|
|
|
# print(bozo)
|
|
|
|
valid = 0
|
|
|
|
else:
|
|
|
|
valid = 1
|
2024-01-06 23:03:08 +01:00
|
|
|
await sqlite.update_feed_validity(
|
|
|
|
db_file, url, valid)
|
|
|
|
if "updated_parsed" in feed["feed"].keys():
|
|
|
|
updated = feed["feed"]["updated_parsed"]
|
|
|
|
updated = convert_struct_time_to_iso8601(updated)
|
|
|
|
else:
|
|
|
|
updated = ''
|
|
|
|
entries = len(feed["entries"])
|
|
|
|
await sqlite.update_feed_properties(
|
|
|
|
db_file, url, entries, updated)
|
2024-01-04 02:16:24 +01:00
|
|
|
except (
|
|
|
|
IncompleteReadError,
|
|
|
|
IncompleteRead,
|
|
|
|
error.URLError
|
|
|
|
) as e:
|
2024-01-06 23:03:08 +01:00
|
|
|
print(e)
|
2024-01-04 02:16:24 +01:00
|
|
|
# TODO Print error to log
|
2024-01-06 23:03:08 +01:00
|
|
|
# None
|
2024-01-04 02:16:24 +01:00
|
|
|
# NOTE I don't think there should be "return"
|
|
|
|
# because then we might stop scanning next URLs
|
|
|
|
# return
|
|
|
|
# TODO Place these couple of lines back down
|
|
|
|
# NOTE Need to correct the SQL statement to do so
|
|
|
|
# NOT SURE WHETHER I MEANT THE LINES ABOVE OR BELOW
|
2024-01-06 23:03:08 +01:00
|
|
|
if status == 200:
|
2024-01-04 02:16:24 +01:00
|
|
|
# NOT SURE WHETHER I MEANT THE LINES ABOVE OR BELOW
|
|
|
|
# TODO Place these couple of lines back down
|
|
|
|
# NOTE Need to correct the SQL statement to do so
|
|
|
|
entries = feed.entries
|
|
|
|
# length = len(entries)
|
|
|
|
# await remove_entry(db_file, source, length)
|
2024-01-04 13:38:22 +01:00
|
|
|
await remove_nonexistent_entries(
|
2024-01-06 23:03:08 +01:00
|
|
|
db_file, feed, url)
|
2024-01-04 02:16:24 +01:00
|
|
|
# new_entry = 0
|
|
|
|
for entry in entries:
|
|
|
|
# TODO Pass date too for comparion check
|
|
|
|
if entry.has_key("published"):
|
|
|
|
date = entry.published
|
|
|
|
date = rfc2822_to_iso8601(date)
|
|
|
|
elif entry.has_key("updated"):
|
|
|
|
date = entry.updated
|
|
|
|
date = rfc2822_to_iso8601(date)
|
|
|
|
else:
|
|
|
|
# TODO Just set date = "*** No date ***"
|
|
|
|
# date = await datetime.now().isoformat()
|
|
|
|
date = now()
|
|
|
|
# NOTE Would seconds result in better database performance
|
|
|
|
# date = datetime.datetime(date)
|
|
|
|
# date = (date-datetime.datetime(1970,1,1)).total_seconds()
|
|
|
|
if entry.has_key("title"):
|
|
|
|
title = entry.title
|
|
|
|
# title = "{}: *{}*".format(feed["feed"]["title"], entry.title)
|
|
|
|
else:
|
|
|
|
title = date
|
|
|
|
# title = feed["feed"]["title"]
|
|
|
|
if entry.has_key("link"):
|
|
|
|
# link = complete_url(source, entry.link)
|
2024-01-06 23:03:08 +01:00
|
|
|
link = join_url(url, entry.link)
|
2024-01-04 02:16:24 +01:00
|
|
|
link = trim_url(link)
|
|
|
|
else:
|
2024-01-06 23:03:08 +01:00
|
|
|
link = url
|
2024-01-04 02:16:24 +01:00
|
|
|
if entry.has_key("id"):
|
|
|
|
eid = entry.id
|
|
|
|
else:
|
|
|
|
eid = link
|
|
|
|
exist = await sqlite.check_entry_exist(
|
2024-01-06 23:03:08 +01:00
|
|
|
db_file, url, eid=eid,
|
2024-01-04 02:16:24 +01:00
|
|
|
title=title, link=link, date=date)
|
|
|
|
if not exist:
|
|
|
|
# new_entry = new_entry + 1
|
|
|
|
# TODO Enhance summary
|
|
|
|
if entry.has_key("summary"):
|
|
|
|
summary = entry.summary
|
|
|
|
# # Remove HTML tags
|
|
|
|
# summary = BeautifulSoup(summary, "lxml").text
|
|
|
|
# # TODO Limit text length
|
|
|
|
# summary = summary.replace("\n\n\n", "\n\n")
|
|
|
|
# summary = summary[:300] + " […]⃨"
|
|
|
|
# summary = summary.strip().split('\n')
|
|
|
|
# summary = ["> " + line for line in summary]
|
|
|
|
# summary = "\n".join(summary)
|
|
|
|
else:
|
|
|
|
summary = "> *** No summary ***"
|
|
|
|
read_status = 0
|
|
|
|
pathname = urlsplit(link).path
|
2024-01-04 13:38:22 +01:00
|
|
|
string = ("{} {} {}"
|
|
|
|
).format(
|
|
|
|
title, summary, pathname
|
|
|
|
)
|
|
|
|
allow_list = await config.is_include_keyword(
|
2024-01-04 02:16:24 +01:00
|
|
|
db_file, "filter-allow", string)
|
|
|
|
if not allow_list:
|
2024-01-04 13:38:22 +01:00
|
|
|
reject_list = await config.is_include_keyword(
|
2024-01-04 02:16:24 +01:00
|
|
|
db_file, "filter-deny", string)
|
|
|
|
if reject_list:
|
|
|
|
# print(">>> REJECTED", title)
|
|
|
|
summary = (
|
|
|
|
"REJECTED {}".format(
|
|
|
|
reject_list.upper()
|
|
|
|
)
|
|
|
|
)
|
|
|
|
# summary = ""
|
|
|
|
read_status = 1
|
|
|
|
entry = (
|
2024-01-06 23:03:08 +01:00
|
|
|
title, link, eid, url, date, read_status)
|
2024-01-04 02:16:24 +01:00
|
|
|
if isinstance(date, int):
|
|
|
|
print("PROBLEM: date is int")
|
|
|
|
print(date)
|
|
|
|
# breakpoint()
|
|
|
|
# print(source)
|
|
|
|
# print(date)
|
|
|
|
await sqlite.add_entry_and_set_date(
|
2024-01-06 23:03:08 +01:00
|
|
|
db_file, url, entry)
|
2024-01-04 02:16:24 +01:00
|
|
|
# print(current_time(), entry, title)
|
|
|
|
# else:
|
|
|
|
# print(current_time(), exist, title)
|
|
|
|
|
|
|
|
|
2024-01-06 23:03:08 +01:00
|
|
|
async def remove_nonexistent_entries(db_file, feed, url):
|
2024-01-04 13:38:22 +01:00
|
|
|
"""
|
|
|
|
Remove entries that don't exist in a given parsed feed.
|
|
|
|
Check the entries returned from feed and delete read non
|
|
|
|
existing entries, otherwise move to table archive, if unread.
|
|
|
|
|
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
db_file : str
|
|
|
|
Path to database file.
|
|
|
|
feed : list
|
|
|
|
Parsed feed document.
|
2024-01-06 23:03:08 +01:00
|
|
|
url : str
|
2024-01-04 13:38:22 +01:00
|
|
|
Feed URL. URL of associated feed.
|
|
|
|
"""
|
2024-01-06 23:03:08 +01:00
|
|
|
items = await sqlite.get_entries_of_feed(db_file, feed, url)
|
2024-01-04 13:38:22 +01:00
|
|
|
entries = feed.entries
|
|
|
|
# breakpoint()
|
|
|
|
for item in items:
|
|
|
|
valid = False
|
|
|
|
for entry in entries:
|
|
|
|
title = None
|
|
|
|
link = None
|
|
|
|
time = None
|
|
|
|
# valid = False
|
|
|
|
# TODO better check and don't repeat code
|
|
|
|
if entry.has_key("id") and item[3]:
|
|
|
|
if entry.id == item[3]:
|
|
|
|
# print("compare1:", entry.id)
|
|
|
|
# print("compare2:", item[3])
|
|
|
|
# print("============")
|
|
|
|
valid = True
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
if entry.has_key("title"):
|
|
|
|
title = entry.title
|
|
|
|
else:
|
|
|
|
title = feed["feed"]["title"]
|
|
|
|
if entry.has_key("link"):
|
2024-01-06 23:03:08 +01:00
|
|
|
link = join_url(url, entry.link)
|
2024-01-04 13:38:22 +01:00
|
|
|
else:
|
2024-01-06 23:03:08 +01:00
|
|
|
link = url
|
2024-01-04 13:38:22 +01:00
|
|
|
if entry.has_key("published") and item[4]:
|
|
|
|
# print("compare11:", title, link, time)
|
|
|
|
# print("compare22:", item[1], item[2], item[4])
|
|
|
|
# print("============")
|
|
|
|
time = rfc2822_to_iso8601(entry.published)
|
|
|
|
if (item[1] == title and
|
|
|
|
item[2] == link and
|
|
|
|
item[4] == time):
|
|
|
|
valid = True
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
if (item[1] == title and
|
|
|
|
item[2] == link):
|
|
|
|
# print("compare111:", title, link)
|
|
|
|
# print("compare222:", item[1], item[2])
|
|
|
|
# print("============")
|
|
|
|
valid = True
|
|
|
|
break
|
|
|
|
# TODO better check and don't repeat code
|
|
|
|
if not valid:
|
|
|
|
# print("id: ", item[0])
|
|
|
|
# if title:
|
|
|
|
# print("title: ", title)
|
|
|
|
# print("item[1]: ", item[1])
|
|
|
|
# if link:
|
|
|
|
# print("link: ", link)
|
|
|
|
# print("item[2]: ", item[2])
|
|
|
|
# if entry.id:
|
|
|
|
# print("last_entry:", entry.id)
|
|
|
|
# print("item[3]: ", item[3])
|
|
|
|
# if time:
|
|
|
|
# print("time: ", time)
|
|
|
|
# print("item[4]: ", item[4])
|
|
|
|
# print("read: ", item[5])
|
|
|
|
# breakpoint()
|
|
|
|
|
|
|
|
# TODO Send to table archive
|
|
|
|
# TODO Also make a regular/routine check for sources that
|
|
|
|
# have been changed (though that can only happen when
|
|
|
|
# manually editing)
|
|
|
|
ix = item[0]
|
|
|
|
# print(">>> SOURCE: ", source)
|
|
|
|
# print(">>> INVALID:", item[1])
|
|
|
|
# print("title:", item[1])
|
|
|
|
# print("link :", item[2])
|
|
|
|
# print("id :", item[3])
|
|
|
|
if item[5] == 1:
|
2024-01-06 23:03:08 +01:00
|
|
|
await sqlite.delete_entry_by_id(db_file, ix)
|
2024-01-04 13:38:22 +01:00
|
|
|
# print(">>> DELETING:", item[1])
|
|
|
|
else:
|
|
|
|
# print(">>> ARCHIVING:", item[1])
|
2024-01-06 23:03:08 +01:00
|
|
|
await sqlite.archive_entry(db_file, ix)
|
2024-01-04 13:38:22 +01:00
|
|
|
limit = (
|
|
|
|
await sqlite.get_settings_value(db_file, "archive")
|
|
|
|
) or (
|
|
|
|
config.get_value_default("settings", "Settings", "archive")
|
|
|
|
)
|
|
|
|
await sqlite.maintain_archive(db_file, limit)
|