setop/agenda_culturel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

On ajoute un outil de tracking pour comprendre les erreurs FB

Browse Source
This commit is contained in:
Jean-Marie Favreau 2025-02-19 16:46:40 +01:00
parent 2ace02a5b7
commit 70755b8f5e
1 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
src/agenda_culturel/import_tasks/custom_extractors/fbevents.py
View File

@ -69,15 +69,19 @@ class CExtractor(TwoStepsExtractor):
raise Exception(_("the page was not yet populated with events, so the loading time was probably too short"))
if not self.found and debug:
directory = "errors/"
if not os.path.exists(directory):
os.makedirs(directory)
now = datetime.now()
filename = directory + now.strftime("%Y%m%d_%H%M%S") + ".html"
logger.warning("cannot find any event link in events page. Save content page in " + filename)
with open(filename, "w") as text_file:
text_file.write("<!-- " + self.url + " -->\n\n")
text_file.write(content)
self.dump_content_for_debug(content)
def dump_content_for_debug(self, content):
directory = "errors/"
if not os.path.exists(directory):
os.makedirs(directory)
now = datetime.now()
filename = directory + now.strftime("%Y%m%d_%H%M%S") + ".html"
with open(filename, "w") as text_file:
text_file.write("<!-- " + self.url + " -->\n\n")
text_file.write(content)
@ -90,7 +94,8 @@ class CExtractor(TwoStepsExtractor):
default_values=None,
published=False,
):
debug = True
fevent = None
soup = BeautifulSoup(event_content, "html.parser")
for json_script in soup.find_all("script", type="application/json"):
@ -106,6 +111,7 @@ class CExtractor(TwoStepsExtractor):
self.add_event(default_values, **event)
else:
self.dump_content_for_debug(event_content)
raise Exception(
_("Cannot get Facebook event from {}").format(event_url)
)