Skip to content

Update regex patterns to raw string format #58

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jinh0park wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update regex patterns to raw string format #58

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 12 additions & 12 deletions dart_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,15 +104,15 @@ def sub_docs(rcp_no, match=None):

## 하위 문서 URL 추출
multi_page_re = (
"\s+node[12]\['text'\][ =]+\"(.*?)\"\;"
"\s+node[12]\['id'\][ =]+\"(\d+)\";"
"\s+node[12]\['rcpNo'\][ =]+\"(\d+)\";"
"\s+node[12]\['dcmNo'\][ =]+\"(\d+)\";"
"\s+node[12]\['eleId'\][ =]+\"(\d+)\";"
"\s+node[12]\['offset'\][ =]+\"(\d+)\";"
"\s+node[12]\['length'\][ =]+\"(\d+)\";"
"\s+node[12]\['dtd'\][ =]+\"(.*?)\";"
"\s+node[12]\['tocNo'\][ =]+\"(\d+)\";"
r"\s+node[12]\['text'\][ =]+\"(.*?)\"\;"
r"\s+node[12]\['id'\][ =]+\"(\d+)\";"
r"\s+node[12]\['rcpNo'\][ =]+\"(\d+)\";"
r"\s+node[12]\['dcmNo'\][ =]+\"(\d+)\";"
r"\s+node[12]\['eleId'\][ =]+\"(\d+)\";"
r"\s+node[12]\['offset'\][ =]+\"(\d+)\";"
r"\s+node[12]\['length'\][ =]+\"(\d+)\";"
r"\s+node[12]\['dtd'\][ =]+\"(.*?)\";"
r"\s+node[12]\['tocNo'\][ =]+\"(\d+)\";"
)
matches = re.findall(multi_page_re, r.text)
if len(matches) > 0:
Expand All @@ -129,7 +129,7 @@ def sub_docs(rcp_no, match=None):
df = df.sort_values('similarity', ascending=False)
return df[['title', 'url']]
else:
single_page_re = "\t\tviewDoc\('(\d+)', '(\d+)', '(\d+)', '(\d+)', '(\d+)', '(\S+)',''\)\;"
single_page_re = r"\t\tviewDoc\('(\d+)', '(\d+)', '(\d+)', '(\d+)', '(\d+)', '(\S+)',''\)\;"
matches = re.findall(single_page_re, r.text)
if len(matches) > 0:
doc_title = BeautifulSoup(r.text, features="lxml").title.text.strip()
Expand Down Expand Up @@ -181,8 +181,8 @@ def attach_files(arg): # rcp_no or URL

rcp_no = dcm_no = None
matches = re.findall(
"\s+node[12]\['rcpNo'\][ =]+\"(\d+)\";"
+ "\s+node[12]\['dcmNo'\][ =]+\"(\d+)\";", r.text)
r"\s+node[12]\['rcpNo'\][ =]+\"(\d+)\";"
+ r"\s+node[12]\['dcmNo'\][ =]+\"(\d+)\";", r.text)
if matches:
rcp_no = matches[0][0]
dcm_no = matches[0][1]
Expand Down