Skip to content

Commit f02d4b0

Browse files
mlissnermlissner
authored
Merge pull request #1686 from freelawproject/fix-recap-email-insb-case-number-parsing
fix(email): Fixed docket_number parsing inside nested tags
2 parents d1ca831 + 66e14aa commit f02d4b0

File tree

4 files changed

+156
-3
lines changed

4 files changed

+156
-3
lines changed

‎CHANGES.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -21,7 +21,7 @@ Changes:
2121
-
2222

2323
Fixes:
24-
-
24+
- fix recap.email docket_number parsing inside nested tags
2525

2626

2727
## Current

‎juriscraper/pacer/email.py‎

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -245,13 +245,14 @@ def _parse_docket_number(
245245
return case_number, self._return_default_dn_components()
246246

247247
path = self._sibling_path("Case Number")
248-
docket_numbers_str = current_node.xpath(f"{path}/a/text()")
248+
docket_numbers_str = current_node.xpath(f"{path}/a//text()")
249+
249250
self.raw_docket_numbers.update(set(docket_numbers_str))
250251
docket_number, docket_number_components = (
251252
self._parse_docket_number_strs(docket_numbers_str)
252253
)
253254
if not docket_number:
254-
docket_numbers_str = current_node.xpath(f"{path}/p/a/text()")
255+
docket_numbers_str = current_node.xpath(f"{path}/p/a//text()")
255256
self.raw_docket_numbers.update(set(docket_numbers_str))
256257
docket_number, docket_number_components = (
257258
self._parse_docket_number_strs(docket_numbers_str)

‎tests/examples/pacer/nef/s3/insb_1.json‎

Lines changed: 32 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,32 @@
1+
{
2+
"acms": false,
3+
"appellate": false,
4+
"contains_attachments": false,
5+
"court_id": "insb",
6+
"dockets": [
7+
{
8+
"case_name": "Gerardo Lorenzo Linarducci",
9+
"date_filed": null,
10+
"docket_entries": [
11+
{
12+
"date_filed": "2025-09-25",
13+
"description": "BNC Certificate of Service - OFFICIAL COURT NOTICE (re: Doc [62]). No. of Notices: 2 Notice Date 09/25/2025. (Admin)",
14+
"document_number": "65",
15+
"document_url": "https://ecf.insb.uscourts.gov/doc1/072048850541?pdf_header=&magic_num=62566217&de_seq_num=253&caseid=769408",
16+
"pacer_case_id": "769408",
17+
"pacer_doc_id": "072048850541",
18+
"pacer_magic_num": "62566217",
19+
"pacer_seq_no": "253",
20+
"short_description": "BNC Certificate of Service - OFFICIAL COURT NOTICE"
21+
}
22+
],
23+
"docket_number": "25-03768",
24+
"federal_defendant_number": null,
25+
"federal_dn_case_type": null,
26+
"federal_dn_judge_initials_assigned": "JMC",
27+
"federal_dn_judge_initials_referred": null,
28+
"federal_dn_office_code": null
29+
}
30+
],
31+
"email_recipients": []
32+
}

‎tests/examples/pacer/nef/s3/insb_1.txt‎

Lines changed: 120 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,120 @@
1+
Return-Path: <[email protected]>
2+
Received: from icmecf202.gtwy.uscourts.gov (icmecf202.gtwy.uscourts.gov [63.241.40.205])
3+
by inbound-smtp.us-west-2.amazonaws.com with SMTP id 4ip7k1khkvmgb1gffnb0dhn32fp5en6in98c7v81
4+
for [email protected];
5+
Fri, 26 Sep 2025 04:26:09 +0000 (UTC)
6+
X-SES-Spam-Verdict: PASS
7+
X-SES-Virus-Verdict: PASS
8+
Received-SPF: pass (spfCheck: domain of insb.uscourts.gov designates 63.241.40.205 as permitted sender) client-ip=63.241.40.205; [email protected]; helo=icmecf202.gtwy.uscourts.gov;
9+
Authentication-Results: amazonses.com;
10+
spf=pass (spfCheck: domain of insb.uscourts.gov designates 63.241.40.205 as permitted sender) client-ip=63.241.40.205; [email protected]; helo=icmecf202.gtwy.uscourts.gov;
11+
dkim=pass [email protected];
12+
dmarc=pass header.from=insb.uscourts.gov;
13+
X-SES-RECEIPT: AEFBQUFBQUFBQUFHeTFXbmwvMnRFL1VsN3d1Q20vOTRpUjY0ODVQMmlkVjB3UTNORE5DMU9rcjdxNHhoWVR0Ykx5YXhEMFgzZ1M2WXNSQnlWejVndmlQM2lxNFpSek0zd3Fnc1dpaEl3bzJOSnRUWFZ4K3djaEpwODd2d0dtbFNZQVM1dTdYQzJXSFUzajFpeWdMOW4zc0VvMk13YmNjclNXN0VHNzYzM2VOa1ZNMi9XRERISGpBcW41M0RaMjgvZkFyOUFGcGhTTnlhOERDUEM0dmVBNlVMbEZUVmg5N1RWZC9BZmloeXZKbjBqVnZHL1NBOWFzc25nWFRwV2xib3p1M0txN0J1RUo1Vi9BRkVYZklKellpVDlRNkd3bEpRcFRKMEFicWpnNFpVbzJobEpTU2RlVXc9PQ==
14+
X-SES-DKIM-SIGNATURE: a=rsa-sha256; q=dns/txt; b=r333MUgCz2tfQW0xpmt+3Jqr/RBtrsm+/7z5V/ij6q3Cxsn8XjHHiafuriALbumEVyAd6ZvTzH8MCLU0pRPCC/fI/qcSWDDYPpVd7ic5VzNTIMiuTjtMfDatc0O3axagM9vYGK9Kvwo8aG/kTQXAUaY5B/nyCLd/mGWDY0FCtrU=; c=relaxed/simple; s=gdwg2y3kokkkj5a55z2ilkup5wp5hhxx; d=amazonses.com; t=1758860770; v=1; bh=/RI/7ufuL4OrQ+ueG/FOuUKy7NCz5DL9nXn4qUrl9zU=; h=From:To:Cc:Bcc:Subject:Date:Message-ID:MIME-Version:Content-Type:X-SES-RECEIPT;
15+
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
16+
d=uscourts.gov; [email protected]; q=dns/txt; s=law1w;
17+
t=1758860769; x=1790396769;
18+
h=date:mime-version:from:to:message-id:subject;
19+
bh=nP2c8Cda3f8KDmzicR94zVJZtOCGP9sNOYfV785a8g4=;
20+
b=lLK/uOAU9moLLC4DK8Efqehb4QfDzCzpsaLTY0FWz6Pz79n7FlZDL3J9
21+
mDDrz0tcHsFa0HOGBHK2w/8uZ9f5F9aKlADUELZtk2+dYi2quJa2g+Dob
22+
KJak3KRQ0oPCeFuGxCSqQ2vrHc9yGYLx82GglZQ3DOh0euICKF6zO2EPv
23+
gfXrTmH7e52QCGjz0q71R/TF4KbRrZ6+9B8oBfrzOxyi66KK+47vI0ui/
24+
Ki0qB1RLoPsYkiH7p+D+FJ5MqShRcQOrd4Eh074DS5zKp8stPF4ovQDPP
25+
DW4A9wXzLwqSwUEHAxQfF3xqm0jxYyarhgCX/nR3h6LnQeYwiM+UKK1Sk
26+
A==;
27+
X-CSE-ConnectionGUID: GWg48zENSX2rI0mraVPbWw==
28+
X-CSE-MsgGUID: xBkrcBfDRuuhfctIhiqvXA==
29+
X-SBRS: None
30+
X-REMOTE-IP: 156.119.56.241
31+
Received: from insbdb.insb.gtwy.dcn ([156.119.56.241])
32+
by icmecf202.gtwy.uscourts.gov with ESMTP; 26 Sep 2025 00:26:09 -0400
33+
Received: from insbdb.insb.gtwy.dcn (localhost.localdomain [127.0.0.1])
34+
by insbdb.insb.gtwy.dcn (8.14.7/8.14.7) with ESMTP id 58Q4PDVl052935;
35+
Fri, 26 Sep 2025 00:25:38 -0400
36+
Received: (from ecf_web@localhost)
37+
by insbdb.insb.gtwy.dcn (8.14.7/8.14.4/Submit) id 58Q4OwPG051834;
38+
Fri, 26 Sep 2025 00:24:58 -0400
39+
Date: Fri, 26 Sep 2025 00:24:58 -0400
40+
MIME-Version:1.0
41+
From:[email protected]
42+
To:[email protected]
43+
Message-Id:<[email protected]>
44+
Subject:25-03768-JMC-13 BNC Certificate of Service - OFFICIAL COURT NOTICE
45+
Content-Type: text/html
46+
47+
<p><strong>***NOTE TO PUBLIC ACCESS USERS*** Judicial Conference of the United States policy permits attorneys of record and parties in a case (including pro se litigants) to receive one free electronic copy of all documents filed electronically, if receipt is required by law or directed by the filer. PACER access fees apply to all other users. To avoid later charges, download a copy of each document during this first viewing. However, if the referenced document is a transcript, the free copy and 30-page limit do not apply.</strong></p>
48+
49+
50+
51+
52+
<p align=center><strong>U.S. Bankruptcy Court</strong></p>
53+
54+
<p align=center><strong>Southern District of Indiana</strong></p>
55+
Notice of Electronic Filing
56+
<BR>
57+
<div>
58+
<BR>The following transaction was received from Admin entered on 09/26/2025 at 00:20 AM EDT and filed on 09/25/2025
59+
60+
<BR>
61+
62+
63+
64+
<table border=0 cellspacing=0>
65+
<tr><td><strong>Case Name:</strong>
66+
</td><td>Gerardo Lorenzo Linarducci </td></tr>
67+
<tr><td><strong>Case Number:</strong></td><td><A HREF=https://ecf.insb.uscourts.gov/cgi-bin/DktRpt.pl?769408><FONT COLOR=Green>25-03768-JMC-13</FONT></A></td></tr>
68+
69+
<tr><td><strong>Document Number:</strong></td>
70+
<td>
71+
<a href='https://ecf.insb.uscourts.gov/doc1/072048850541?pdf_header=&magic_num=62566217&de_seq_num=253&caseid=769408'>65</a>
72+
</td></tr>
73+
</table>
74+
75+
76+
77+
78+
<p><strong>Docket Text:</strong>
79+
80+
<BR>
81+
BNC Certificate of Service - OFFICIAL COURT NOTICE (re: Doc # [62]). <i></i> No. of Notices: 2 Notice Date 09/25/2025. (Admin)
82+
</p>
83+
84+
<p>The following document(s) are associated with this transaction:</p>
85+
<table>
86+
<STRONG>Document description:</STRONG>Imaged Certificate of Notice
87+
<BR><STRONG>Original filename:</STRONG>P12503768SF002000246.pdf
88+
<BR><STRONG>Electronic document Stamp:</STRONG>
89+
<BR>[STAMP bkecfStamp_ID=1072195184 [Date=9/26/2025] [FileNumber=47721030-0] [9ebfb1e27f8e83afeecb350ad30ab5fb35e6b542b6b2cd91fd30d4132988837dfc47fee2804e4a68b0ad2c3ec9c9a973ce14c17397250de933a1051d0df9a7e1]]
90+
<BR>
91+
92+
</table>
93+
</div>
94+
95+
96+
97+
98+
<BR><B>
99+
25-03768-JMC-13 Notice will be electronically mailed to:
100+
</B>
101+
102+
<BR>
103+
<B>
104+
25-03768-JMC-13 Notice will not be electronically mailed to:
105+
</B>
106+
107+
<BR>
108+
109+
<BR><span class="personName">Craig Eugene Thomas</span>
110+
<BR>6304 W Cedar Chase Dr
111+
<BR>McCordsville, IN 46163-9284
112+
<BR>
113+
114+
<BR>
115+
<B>
116+
20-01963-JMC-11 These participants in a related case have chosen not to receive notice from this case:
117+
</B>
118+
119+
<BR>
120+
<BR>

0 commit comments

Comments
 (0)