summaryrefslogtreecommitdiffstats
path: root/parsers/logbooks.py
diff options
context:
space:
mode:
authorExpo laptop Crowley <cucc.expedition@gmail.com>2023-07-09 11:30:50 +0200
committerExpo laptop Crowley <cucc.expedition@gmail.com>2023-07-09 11:30:50 +0200
commit4d48dd43867ee8c25202b2b18c9407bee0278240 (patch)
tree66763ca09612a1cebd0863c4f06b8522cefbc080 /parsers/logbooks.py
parent086537cb5633d7c40a692501bacd126291f5f0a7 (diff)
downloadtroggle-4d48dd43867ee8c25202b2b18c9407bee0278240.tar.gz
troggle-4d48dd43867ee8c25202b2b18c9407bee0278240.tar.bz2
troggle-4d48dd43867ee8c25202b2b18c9407bee0278240.zip
Logbook debugging
Diffstat (limited to 'parsers/logbooks.py')
-rw-r--r--parsers/logbooks.py10
1 files changed, 5 insertions, 5 deletions
diff --git a/parsers/logbooks.py b/parsers/logbooks.py
index e7c7363..5b9bb6e 100644
--- a/parsers/logbooks.py
+++ b/parsers/logbooks.py
@@ -57,7 +57,7 @@ LOGBOOK_PARSER_SETTINGS = {
LOGBOOKS_DIR = "years" # subfolder of settings.EXPOWEB
ENTRIES = {
- "2023": 1,
+ "2023": 11,
"2022": 90,
"2019": 55,
"2018": 95,
@@ -295,7 +295,7 @@ def parser_html(year, expedition, txt, seq=""):
headmatch = re.match(r"(?i)(?s).*<body[^>]*>(.*?)<hr.*", txt)
headpara = headmatch.groups()[0].strip()
- # print(f" - headpara:\n'{headpara}'")
+ #print(f" - headpara:\n'{headpara}'")
if len(headpara) > 0:
frontpath = Path(settings.EXPOWEB, LOGBOOKS_DIR, year, "frontmatter.html")
with open(frontpath, "w") as front:
@@ -305,7 +305,7 @@ def parser_html(year, expedition, txt, seq=""):
endmatch = re.match(r"(?i)(?s).*<hr\s*/>([\s\S]*?)(?=</body)", txt)
endpara = endmatch.groups()[0].strip()
- # print(f" - endpara:\n'{endpara}'")
+ #print(f" - endpara:\n'{endpara}'")
if len(endpara) > 0:
endpath = Path(settings.EXPOWEB, LOGBOOKS_DIR, year, "endmatter.html")
with open(endpath, "w") as end:
@@ -333,7 +333,7 @@ def parser_html(year, expedition, txt, seq=""):
if s:
tripid, tripid1, tripdate, trippeople, triptitle, triptext, tu = s.groups()
else: # allow title and people to be swapped in order
- msg = f" !- {year} Can't parse:{logbook_entry_count} '{trippara[:50]}'..."
+ msg = f" !- {year} Can't parse:{logbook_entry_count} '{trippara[:55]}'...'{trippara}'"
print(msg)
DataIssue.objects.create(parser="logbooks", message=msg)
@@ -353,7 +353,7 @@ def parser_html(year, expedition, txt, seq=""):
tripid, tripid1, tripdate, triptitle, trippeople, triptext, tu = s2.groups()
else:
# if not re.search(r"Rigging Guide", trippara):
- msg = f" !- Logbook. Can't parse entry on 2nd pass:{logbook_entry_count} '{trippara[:50]}'..."
+ msg = f" !- Logbook. Can't parse entry on 2nd pass:{logbook_entry_count} '{trippara[:55]}'...'{trippara}'"
print(msg)
DataIssue.objects.create(parser="logbooks", message=msg)
continue