mirror of
https://github.com/polyjitter/searchbot-discord.git
synced 2024-08-14 22:46:55 +00:00
Comment out old search
This commit is contained in:
Adriene Hutchins
parent
fb93adecbe
commit
13e64461be
1 changed files with 178 additions and 178 deletions
356
old_search.py
356
old_search.py
|
|
@ -1,211 +1,211 @@
|
|||
# This is the old search logic for reference purposes
|
||||
|
||||
async def _old_search_logic(self, query: str, is_nsfw: bool = False,
|
||||
category: str = None) -> str:
|
||||
"""Provides search logic for all search commands."""
|
||||
# # This is the old search logic for reference purposes
|
||||
|
||||
# NSFW Filtering
|
||||
# WARNING - This list includes slurs.
|
||||
nono_words = [
|
||||
'tranny', 'faggot', 'fag',
|
||||
'porn', 'cock', 'dick',
|
||||
'titty', 'boob', 'penis',
|
||||
'slut', 'cum', 'jizz',
|
||||
'semen', 'cooch', 'coochie',
|
||||
'pussy', 'penis', 'fetish',
|
||||
'bdsm', 'sexy', 'xxx',
|
||||
'orgasm', 'masturbation',
|
||||
'erotic', 'creampie',
|
||||
'fap', 'nude', 'orgasm',
|
||||
'squirting', 'yiff',
|
||||
'e621'
|
||||
]
|
||||
nono_sites = [
|
||||
'xvideos', 'pornhub',
|
||||
'xhamster', 'xnxx',
|
||||
'youporn', 'xxx',
|
||||
'freexcafe', 'sex.com',
|
||||
'e621', 'nhentai'
|
||||
]
|
||||
# async def _old_search_logic(self, query: str, is_nsfw: bool = False,
|
||||
# category: str = None) -> str:
|
||||
# """Provides search logic for all search commands."""
|
||||
|
||||
if not is_nsfw:
|
||||
for i in nono_words:
|
||||
if i in query.replace(" ", ""):
|
||||
return (
|
||||
"**Sorry!** That query included language "
|
||||
"we cannot accept in a non-NSFW channel. "
|
||||
"Please try again in an NSFW channel."
|
||||
)
|
||||
# # NSFW Filtering
|
||||
# # WARNING - This list includes slurs.
|
||||
# nono_words = [
|
||||
# 'tranny', 'faggot', 'fag',
|
||||
# 'porn', 'cock', 'dick',
|
||||
# 'titty', 'boob', 'penis',
|
||||
# 'slut', 'cum', 'jizz',
|
||||
# 'semen', 'cooch', 'coochie',
|
||||
# 'pussy', 'penis', 'fetish',
|
||||
# 'bdsm', 'sexy', 'xxx',
|
||||
# 'orgasm', 'masturbation',
|
||||
# 'erotic', 'creampie',
|
||||
# 'fap', 'nude', 'orgasm',
|
||||
# 'squirting', 'yiff',
|
||||
# 'e621'
|
||||
# ]
|
||||
# nono_sites = [
|
||||
# 'xvideos', 'pornhub',
|
||||
# 'xhamster', 'xnxx',
|
||||
# 'youporn', 'xxx',
|
||||
# 'freexcafe', 'sex.com',
|
||||
# 'e621', 'nhentai'
|
||||
# ]
|
||||
|
||||
# Choose an instance
|
||||
if self.instances == []:
|
||||
with open('searxes.txt') as f:
|
||||
self.instances = f.read().split('\n')
|
||||
instance = random.sample(self.instances, k=1)[0]
|
||||
# if not is_nsfw:
|
||||
# for i in nono_words:
|
||||
# if i in query.replace(" ", ""):
|
||||
# return (
|
||||
# "**Sorry!** That query included language "
|
||||
# "we cannot accept in a non-NSFW channel. "
|
||||
# "Please try again in an NSFW channel."
|
||||
# )
|
||||
|
||||
# Error Template
|
||||
error_msg = (
|
||||
"**An error occured!**\n\n"
|
||||
f"There was a problem with `{instance}`. Please try again later.\n"
|
||||
f"_If problems with this instance persist, "
|
||||
f"contact`{self.bot.appinfo.owner}` to have it removed._"
|
||||
)
|
||||
# # Choose an instance
|
||||
# if self.instances == []:
|
||||
# with open('searxes.txt') as f:
|
||||
# self.instances = f.read().split('\n')
|
||||
# instance = random.sample(self.instances, k=1)[0]
|
||||
|
||||
# Create the URL to make an API call to
|
||||
call = f'{instance}search?q={query}&format=json&language=en-US'
|
||||
# # Error Template
|
||||
# error_msg = (
|
||||
# "**An error occured!**\n\n"
|
||||
# f"There was a problem with `{instance}`. Please try again later.\n"
|
||||
# f"_If problems with this instance persist, "
|
||||
# f"contact`{self.bot.appinfo.owner}` to have it removed._"
|
||||
# )
|
||||
|
||||
# If a type is provided, add that type to the call URL
|
||||
if category:
|
||||
call += f'&categories={category}'
|
||||
# # Create the URL to make an API call to
|
||||
# call = f'{instance}search?q={query}&format=json&language=en-US'
|
||||
|
||||
if is_nsfw:
|
||||
call += '&safesearch=0'
|
||||
else:
|
||||
call += '&safesearch=1'
|
||||
# # If a type is provided, add that type to the call URL
|
||||
# if category:
|
||||
# call += f'&categories={category}'
|
||||
|
||||
# Figure out engines for different categories to get decent results.
|
||||
if category == 'videos':
|
||||
call += '&engines=bing+videos,google+videos'
|
||||
# Make said API call
|
||||
try:
|
||||
async with self.request.get(call) as resp:
|
||||
response = await resp.json()
|
||||
except aiohttp.ClientError:
|
||||
return error_msg
|
||||
# if is_nsfw:
|
||||
# call += '&safesearch=0'
|
||||
# else:
|
||||
# call += '&safesearch=1'
|
||||
|
||||
# Split our response data up for parsing
|
||||
# infoboxes = response['infoboxes']
|
||||
results = response['results']
|
||||
# # Figure out engines for different categories to get decent results.
|
||||
# if category == 'videos':
|
||||
# call += '&engines=bing+videos,google+videos'
|
||||
# # Make said API call
|
||||
# try:
|
||||
# async with self.request.get(call) as resp:
|
||||
# response = await resp.json()
|
||||
# except aiohttp.ClientError:
|
||||
# return error_msg
|
||||
|
||||
# Create message with results
|
||||
try:
|
||||
# Handle tiny result count
|
||||
if len(results) > 5:
|
||||
amt = 5
|
||||
else:
|
||||
amt = len(results)
|
||||
# # Split our response data up for parsing
|
||||
# # infoboxes = response['infoboxes']
|
||||
# results = response['results']
|
||||
|
||||
# Remove no-no sites
|
||||
if not is_nsfw:
|
||||
for r in results[0:7]:
|
||||
for n in nono_sites:
|
||||
if n in r['url']:
|
||||
results.remove(r)
|
||||
# # Create message with results
|
||||
# try:
|
||||
# # Handle tiny result count
|
||||
# if len(results) > 5:
|
||||
# amt = 5
|
||||
# else:
|
||||
# amt = len(results)
|
||||
|
||||
# Escape stuff
|
||||
query = discord.utils.escape_mentions(query)
|
||||
query = discord.utils.escape_markdown(query)
|
||||
# # Remove no-no sites
|
||||
# if not is_nsfw:
|
||||
# for r in results[0:7]:
|
||||
# for n in nono_sites:
|
||||
# if n in r['url']:
|
||||
# results.remove(r)
|
||||
|
||||
# Header
|
||||
msg = f"Showing **{amt}** results for `{query}`. \n\n"
|
||||
# Expanded Result
|
||||
msg += (
|
||||
f"**{results[0]['title']}** <{results[0]['url']}>\n"
|
||||
f"{results[0]['content']}\n\n")
|
||||
# Other Results
|
||||
msg += "\n".join(
|
||||
[f"**{entry['title']}** <{entry['url']}>" for entry in results[1:5]])
|
||||
# Instance Info
|
||||
msg += f"\n\n_Results retrieved from instance `{instance}`._"
|
||||
# # Escape stuff
|
||||
# query = discord.utils.escape_mentions(query)
|
||||
# query = discord.utils.escape_markdown(query)
|
||||
|
||||
return msg
|
||||
# # Header
|
||||
# msg = f"Showing **{amt}** results for `{query}`. \n\n"
|
||||
# # Expanded Result
|
||||
# msg += (
|
||||
# f"**{results[0]['title']}** <{results[0]['url']}>\n"
|
||||
# f"{results[0]['content']}\n\n")
|
||||
# # Other Results
|
||||
# msg += "\n".join(
|
||||
# [f"**{entry['title']}** <{entry['url']}>" for entry in results[1:5]])
|
||||
# # Instance Info
|
||||
# msg += f"\n\n_Results retrieved from instance `{instance}`._"
|
||||
|
||||
# Reached if error with returned results
|
||||
except (KeyError, IndexError) as e:
|
||||
# Logging
|
||||
self.warn(
|
||||
f"A user encountered a(n) `{e}` with <{instance}> when searching for `{query}`. "
|
||||
"Consider removing it or looking into it.",
|
||||
name="Failed Instance"
|
||||
)
|
||||
# return msg
|
||||
|
||||
self.instances.remove(instance) # Weed the instance out
|
||||
# Recurse until good response
|
||||
return await self._old_search_logic(query, is_nsfw)
|
||||
# # Reached if error with returned results
|
||||
# except (KeyError, IndexError) as e:
|
||||
# # Logging
|
||||
# self.warn(
|
||||
# f"A user encountered a(n) `{e}` with <{instance}> when searching for `{query}`. "
|
||||
# "Consider removing it or looking into it.",
|
||||
# name="Failed Instance"
|
||||
# )
|
||||
|
||||
async def _instance_check(self, instance: str, content: dict) -> bool:
|
||||
"""Checks the quality of an instance."""
|
||||
# self.instances.remove(instance) # Weed the instance out
|
||||
# # Recurse until good response
|
||||
# return await self._old_search_logic(query, is_nsfw)
|
||||
|
||||
# Makes sure proper values exist
|
||||
if 'error' in content:
|
||||
return False
|
||||
if not ('engines' in content and 'initial' in content['timing']):
|
||||
return False
|
||||
if not ('google' in content['engines'] and 'enabled' in content['engines']['google']):
|
||||
return False
|
||||
# async def _instance_check(self, instance: str, content: dict) -> bool:
|
||||
# """Checks the quality of an instance."""
|
||||
|
||||
# Makes sure google is enabled
|
||||
if not content['engines']['google']['enabled']:
|
||||
return False
|
||||
# # Makes sure proper values exist
|
||||
# if 'error' in content:
|
||||
# return False
|
||||
# if not ('engines' in content and 'initial' in content['timing']):
|
||||
# return False
|
||||
# if not ('google' in content['engines'] and 'enabled' in content['engines']['google']):
|
||||
# return False
|
||||
|
||||
# Makes sure is not Tor
|
||||
if content['network_type'] != 'normal':
|
||||
return False
|
||||
# # Makes sure google is enabled
|
||||
# if not content['engines']['google']['enabled']:
|
||||
# return False
|
||||
|
||||
# Only picks instances that are fast enough
|
||||
timing = int(content['timing']['initial'])
|
||||
if timing > 0.20:
|
||||
return False
|
||||
# # Makes sure is not Tor
|
||||
# if content['network_type'] != 'normal':
|
||||
# return False
|
||||
|
||||
# Check for Google captcha
|
||||
test_search = f'{instance}/search?q=test&format=json&lang=en-US'
|
||||
try:
|
||||
async with self.request.get(test_search) as resp:
|
||||
response = await resp.json()
|
||||
response['results'][0]['content']
|
||||
except (aiohttp.ClientError, KeyError, IndexError):
|
||||
return False
|
||||
# # Only picks instances that are fast enough
|
||||
# timing = int(content['timing']['initial'])
|
||||
# if timing > 0.20:
|
||||
# return False
|
||||
|
||||
# Reached if passes all checks
|
||||
return True
|
||||
# # Check for Google captcha
|
||||
# test_search = f'{instance}/search?q=test&format=json&lang=en-US'
|
||||
# try:
|
||||
# async with self.request.get(test_search) as resp:
|
||||
# response = await resp.json()
|
||||
# response['results'][0]['content']
|
||||
# except (aiohttp.ClientError, KeyError, IndexError):
|
||||
# return False
|
||||
|
||||
@commands.command()
|
||||
@commands.is_owner()
|
||||
async def rejson(self, ctx):
|
||||
"""Refreshes the list of instances for searx."""
|
||||
# # Reached if passes all checks
|
||||
# return True
|
||||
|
||||
msg = await ctx.send('<a:updating:403035325242540032> Refreshing instance list...\n\n'
|
||||
'(Due to extensive quality checks, this may take a bit.)')
|
||||
plausible: List[str] = []
|
||||
# @commands.command()
|
||||
# @commands.is_owner()
|
||||
# async def rejson(self, ctx):
|
||||
# """Refreshes the list of instances for searx."""
|
||||
|
||||
# Get, parse, and quality check all instances
|
||||
async with self.request.get('https://searx.space/data/instances.json') as r:
|
||||
# Parsing
|
||||
searx_json = await r.json()
|
||||
instances = searx_json['instances']
|
||||
# msg = await ctx.send('<a:updating:403035325242540032> Refreshing instance list...\n\n'
|
||||
# '(Due to extensive quality checks, this may take a bit.)')
|
||||
# plausible: List[str] = []
|
||||
|
||||
# Quality Check
|
||||
for i in instances:
|
||||
content = instances.get(i)
|
||||
is_good: bool = await self._instance_check(i, content)
|
||||
if is_good:
|
||||
plausible.append(i)
|
||||
# # Get, parse, and quality check all instances
|
||||
# async with self.request.get('https://searx.space/data/instances.json') as r:
|
||||
# # Parsing
|
||||
# searx_json = await r.json()
|
||||
# instances = searx_json['instances']
|
||||
|
||||
# Save new list
|
||||
self.instances = plausible
|
||||
with open('searxes.txt', 'w') as f:
|
||||
f.write('\n'.join(plausible))
|
||||
# # Quality Check
|
||||
# for i in instances:
|
||||
# content = instances.get(i)
|
||||
# is_good: bool = await self._instance_check(i, content)
|
||||
# if is_good:
|
||||
# plausible.append(i)
|
||||
|
||||
await msg.edit(content='Instances refreshed!')
|
||||
# # Save new list
|
||||
# self.instances = plausible
|
||||
# with open('searxes.txt', 'w') as f:
|
||||
# f.write('\n'.join(plausible))
|
||||
|
||||
async def _old_basic_search(self, ctx, query: str,
|
||||
category: str = None):
|
||||
"""Base search message generation."""
|
||||
# await msg.edit(content='Instances refreshed!')
|
||||
|
||||
async with ctx.typing():
|
||||
is_nsfw = (
|
||||
ctx.channel.is_nsfw() if hasattr(ctx.channel, 'is_nsfw')
|
||||
else False
|
||||
)
|
||||
# async def _old_basic_search(self, ctx, query: str,
|
||||
# category: str = None):
|
||||
# """Base search message generation."""
|
||||
|
||||
msg = await self._old_search_logic(query, is_nsfw, category)
|
||||
await ctx.send(msg)
|
||||
# async with ctx.typing():
|
||||
# is_nsfw = (
|
||||
# ctx.channel.is_nsfw() if hasattr(ctx.channel, 'is_nsfw')
|
||||
# else False
|
||||
# )
|
||||
|
||||
self.info(
|
||||
content=(
|
||||
f"**{ctx.author}** searched for `{query}` "
|
||||
f"in \"{ctx.guild}\" and got this:"
|
||||
f"\n\n{msg}"
|
||||
),
|
||||
name="Search Results"
|
||||
)
|
||||
# msg = await self._old_search_logic(query, is_nsfw, category)
|
||||
# await ctx.send(msg)
|
||||
|
||||
# self.info(
|
||||
# content=(
|
||||
# f"**{ctx.author}** searched for `{query}` "
|
||||
# f"in \"{ctx.guild}\" and got this:"
|
||||
# f"\n\n{msg}"
|
||||
# ),
|
||||
# name="Search Results"
|
||||
# )
|
||||
|
|
|
|||
Loading…
Reference in a new issue