Mirrors/kleinanzeigen-bot
1
0
Fork 0
mirror of https://github.com/Second-Hand-Friends/kleinanzeigen-bot.git synced 2026-03-12 10:31:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix: special attributes cannot be parsed as JSON #312

Browse Source
This commit is contained in:
Saghalt
2024-06-11 10:55:03 +02:00
committed by GitHub
parent 0f87e5573a
commit eab9874bdb
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/kleinanzeigen_bot/extract.py
View File

@@ -3,7 +3,7 @@ SPDX-FileCopyrightText: © Sebastian Thomschke and contributors
SPDX-License-Identifier: AGPL-3.0-or-later SPDX-License-Identifier: AGPL-3.0-or-later
SPDX-ArtifactOfProjectHomePage: https://github.com/Second-Hand-Friends/kleinanzeigen-bot/ SPDX-ArtifactOfProjectHomePage: https://github.com/Second-Hand-Friends/kleinanzeigen-bot/
""" """
import json, logging, os, shutil import json, logging, os, shutil, re
import urllib.request as urllib_request import urllib.request as urllib_request
from datetime import datetime from datetime import datetime
from typing import Any, Final from typing import Any, Final
@@ -290,7 +290,9 @@ class AdExtractor(WebScrapingMixin):
""" """
belen_conf = await self.web_execute("window.BelenConf") belen_conf = await self.web_execute("window.BelenConf")
special_attributes_str = belen_conf["universalAnalyticsOpts"]["dimensions"]["dimension108"] special_attributes_str = belen_conf["universalAnalyticsOpts"]["dimensions"]["dimension108"]
special_attributes = json.loads(special_attributes_str) # Surrounding any word with " and add curly braces
special_attributes_fixed_str = "{" + re.sub('(\\w+)', '"\\g<1>"', special_attributes_str) + "}"
special_attributes = json.loads(special_attributes_fixed_str)
if not isinstance(special_attributes, dict): if not isinstance(special_attributes, dict):
raise ValueError( raise ValueError(
"Failed to parse special attributes from ad page." "Failed to parse special attributes from ad page."