def import_law_box_case(case_path, i):
raw_text = open(case_path).read()
clean_html_tree, complete_html_tree, clean_html_str, body_text = get_html_from_raw_text(
raw_text)
citations = get_citations_from_tree(complete_html_tree, case_path)
if not citations:
print "******** F: %s ********" % case_path
"""
def import_law_box_case(case_path, i):
raw_text = open(case_path).read()
clean_html_tree, complete_html_tree, clean_html_str, body_text = get_html_from_raw_text(raw_text)
citations = get_citations_from_tree(complete_html_tree, case_path)
if not citations:
print "******** F: %s ********" % case_path
"""
def import_law_box_case(case_path):
"""Open the file, get its contents, convert to XML and extract the meta data.
Return a document object for saving in the database
"""
raw_text = open(case_path).read()
clean_html_tree, complete_html_tree, clean_html_str, body_text = get_html_from_raw_text(
raw_text)
sha1 = hashlib.sha1(clean_html_str).hexdigest()
citations = get_citations_from_tree(complete_html_tree, case_path)
judges = get_judge(clean_html_tree, case_path)
court = get_court_object(clean_html_tree, citations, case_path, judges)
doc = Document(
source='L',
sha1=sha1,
html=
clean_html_str, # we clear this field later, putting the value into html_lawbox.
date_filed=get_date_filed(clean_html_tree,
citations=citations,
case_path=case_path,
court=court),
precedential_status=get_precedential_status(),
judges=judges,
download_url=case_path,
)
cite = Citation(docket_number=get_docket_number(
clean_html_tree, case_path=case_path, court=court))
docket = Docket(
case_name=get_case_name(complete_html_tree, case_path),
court=court,
)
# Necessary for dup_finder.
path = '//p/text()'
doc.body_text = ' '.join(clean_html_tree.xpath(path))
# Add the dict of citations to the object as its attributes.
citations_as_dict = map_citations_to_models(citations)
for k, v in citations_as_dict.iteritems():
setattr(cite, k, v)
doc.citation = cite
doc.docket = docket
return doc
def import_law_box_case(case_path):
"""Open the file, get its contents, convert to XML and extract the meta data.
Return a document object for saving in the database
"""
raw_text = open(case_path).read()
clean_html_tree, complete_html_tree, clean_html_str, body_text = get_html_from_raw_text(raw_text)
sha1 = hashlib.sha1(clean_html_str).hexdigest()
citations = get_citations_from_tree(complete_html_tree, case_path)
judges = get_judge(clean_html_tree, case_path)
court = get_court_object(clean_html_tree, citations, case_path, judges)
doc = Document(
source='L',
sha1=sha1,
html=clean_html_str, # we clear this field later, putting the value into html_lawbox.
date_filed=get_date_filed(clean_html_tree, citations=citations, case_path=case_path, court=court),
precedential_status=get_precedential_status(),
judges=judges,
download_url=case_path,
)
cite = Citation()
docket = Docket(
docket_number=get_docket_number(
clean_html_tree,
case_path=case_path,
court=court
),
case_name=get_case_name(complete_html_tree, case_path),
court=court,
)
# Necessary for dup_finder.
path = '//p/text()'
doc.body_text = ' '.join(clean_html_tree.xpath(path))
# Add the dict of citations to the object as its attributes.
citations_as_dict = map_citations_to_models(citations)
for k, v in citations_as_dict.iteritems():
setattr(cite, k, v)
doc.citation = cite
doc.docket = docket
return doc
