diff options
Diffstat (limited to 'python')
| -rw-r--r-- | python/quote_parsing/parse_emails.py | 12 |
1 files changed, 8 insertions, 4 deletions
diff --git a/python/quote_parsing/parse_emails.py b/python/quote_parsing/parse_emails.py index defb568f..b206e1f5 100644 --- a/python/quote_parsing/parse_emails.py +++ b/python/quote_parsing/parse_emails.py @@ -156,8 +156,9 @@ def parse_baml_block(fh, indextype): return makedf(r, indextype, "BAML"), line -def parse_bnp_block(fh, indextype): - next(fh) # skip header +def parse_bnp_block(fh, indextype, skip_header=True): + if skip_header: + next(fh) # skip header r = [] for line in fh: line = line.strip() @@ -532,12 +533,15 @@ def parse_bnp(fh, indextype, series, quotedate, expiration_dates): fwd_index = [] d = {"quotedate": quotedate, "index": indextype, "series": series} regex = ( - r"Ref\s(?P<ref>[\d.]+) - (?P<expiry>\w{3}\d{2}) - Fwd\s(?P<fwdspread>[\d.]+)" + r"Ref\s(?P<ref>[\d.]+) -\s+(?P<expiry>\w{3}\d{2}) - Fwd\s(?P<fwdspread>[\d.]+)" ) pat = re.compile(regex) for line in fh: line = line.strip() if line.startswith("Ref"): + c = line.find("Strike") + if c != -1: + line = line[:c].rstrip() m = pat.match(line) if m: d.update(**m.groupdict()) @@ -546,7 +550,7 @@ def parse_bnp(fh, indextype, series, quotedate, expiration_dates): d for d in expiration_dates if d.month == expiry_month ) fwd_index.append(d.copy()) - option_stack[d["expiry"]] = parse_bnp_block(fh, indextype) + option_stack[d["expiry"]] = parse_bnp_block(fh, indextype, c == -1) else: logger.error("Can't parse expiry line:", line, "filename:", fh.name) fwd_index = pd.DataFrame.from_records(fwd_index, index="quotedate") |