def html2text(request):
text = ''
posted_url = request.POST.get('url', '')
if posted_url:
d = Document(posted_url)
text = d.text()
context = Context({
'text' : text
})
template = get_template('html2text.html')
html = template.render(context)
return HttpResponse(html)
def doc(self):
cache_key = "url_" + self.url
cache_doc = cache.get(cache_key)
if cache_doc:
print("Cache hit: URL: " + self.url)
doc = cache_doc
else:
doc = Document(self.url)
cache.set(cache_key, doc, 60)
return doc
def data(self, all_fields=True):
"""
Calculate context of quotation using QuoteContext class
Optionally return a smaller subset of fields to upload to cloud
"""
data_dict = {
'sha1': self.hash(),
'citing_url': self.citing_url,
'cited_url': self.cited_url,
}
# Get text version of document
citing_doc = Document(self.citing_url)
cited_doc = Document(self.cited_url)
# Populate context fields with Document methods
document_fields = ['doc_type', 'text']
quote_context_fields = [
'context_before', 'context_after', # 'quote',
'quote_length',
'quote',
'quote_start_position', 'quote_end_position',
'context_start_position', 'context_end_position',
]
if self.raw_output:
data_dict['citing_raw'] = citing_doc.raw()
data_dict['cited_raw'] = cited_doc.raw()
# if self.text_output:
# quote_context_fields.append('text')
for doc_field in document_fields:
citing_field = ''.join(['citing_', doc_field])
cited_field = ''.join(['cited_', doc_field])
data_dict[citing_field] = citing_doc.data()[doc_field]
data_dict[cited_field] = cited_doc.data()[doc_field]
# Find context of quote from within text
citing_context = QuoteContext(self.citing_quote, citing_doc.text())
cited_context = QuoteContext(self.citing_quote, cited_doc.text())
for field in quote_context_fields:
citing_field = ''.join(['citing_', field])
cited_field = ''.join(['cited_', field])
data_dict[citing_field] = citing_context.data()[field]
data_dict[cited_field] = cited_context.data()[field]
# Stop Elapsed Timer
elapsed_time = time.time() - self.start_time
data_dict['create_elapsed_time'] = format(elapsed_time, '.5f')
if not all_fields:
excluded_fields = [
'cited_raw', 'citing_raw',
'citing_text', 'cited_text',
'citing_quote_length',
'cited_quote_start_position', 'citing_quote_start_position',
'cited_quote_end_position', 'citing_quote_end_position',
'cited_context_start_position',
'citing_context_start_position',
'cited_context_end_position', 'citing_context_end_position',
'create_elapsed_time',
] # 'cited_cache_url', 'cited_archive_url',
for excluded_field in excluded_fields:
data_dict.pop(excluded_field)
return data_dict
def data(self, all_fields=True):
"""
Calculate context of quotation using QuoteContext class
Optionally return a smaller subset of fields to upload to cloud
"""
cached_data = cache.get(self.cache_key())
if cached_data:
print("Returning cached Quote Data: " + self.cited_url)
return cached_data
else:
print("Looking up data() for " + self.cited_url)
data_dict = {
'sha1': self.hash(),
'citing_url': self.citing_url,
'cited_url': self.cited_url,
}
# Get text version of document if text not passed into object
citing_text = self.citing_text
citing_raw = self.citing_raw
print("Populating Document: Doc, Text, Raw")
if (len(citing_text) == 0) or (len(citing_raw) == 0):
citing_text = self.citing_text
citing_raw = self.citing_raw
cited_doc = Document(self.cited_url)
print("3)----data()['text']-----")
cited_text = cited_doc.text()
print("End Populating")
data_dict['citing_text'] = citing_text
data_dict['cited_text'] = cited_text
# Find context of quote from within text
citing_context_data = QuoteContext(self.citing_quote,
citing_text).data()
cited_context_data = QuoteContext(self.citing_quote,
cited_text).data()
# Populate context fields with Document methods
quote_context_fields = [
'context_before',
'context_after', # 'quote',
'quote_length',
'quote',
'quote_start_position',
'quote_end_position',
'context_start_position',
'context_end_position',
]
for field in quote_context_fields:
citing_field = ''.join(['citing_', field])
cited_field = ''.join(['cited_', field])
data_dict[citing_field] = citing_context_data[field]
data_dict[cited_field] = cited_context_data[field]
# Stop Elapsed Timer
elapsed_time = time.time() - self.start_time
data_dict['create_elapsed_time'] = format(elapsed_time, '.5f')
if not all_fields:
excluded_fields = [
'cited_raw',
'citing_raw',
'citing_text',
'cited_text',
'citing_quote_length',
'cited_quote_start_position',
'citing_quote_start_position',
'cited_quote_end_position',
'citing_quote_end_position',
'cited_context_start_position',
'citing_context_start_position',
'cited_context_end_position',
'citing_context_end_position',
'create_elapsed_time',
] # 'cited_cache_url', 'cited_archive_url',
for excluded_field in excluded_fields:
data_dict.pop(excluded_field)
cache.set(self.cache_key(), data_dict, 60)
return data_dict
def raw(self):
raw = ''
doc = Document(self.url)
raw = doc.raw()
return raw
