def get_context(url, matchtext, before, after):
html = get_cached_url(url).read()
textsegments = html_to_text(html)
i = textsegments.find(matchtext)
bigtext = textsegments[max(0, i - before):min(i +
after, len(textsegments))]
return trim_to_words(bigtext)
def get_raw_disputes(url):
"""unfiltered and unranked. Return all disputes we find"""
try:
htmlcontent = urllib2.urlopen(url, None, 2).read(200000)
text = html_to_text(htmlcontent)
return match_with_claims(text)
except:
return []
def get_dispute_context(claimtext):
try:
contextobj = ClaimContext.objects.filter(claimtext=claimtext)[0]
text = html_to_text(contextobj.sentence).strip()
return {'url':contextobj.url, 'text':text, 'prefix': contextobj.prefix, 'date':contextobj.date,
'badvotes':contextobj.badvotes, 'goodvotes':contextobj.goodvotes}
except:
return {'url':'',"text":'','prefix':'','date':'','badvotes':0,'goodvotes':0}
def get_raw_disputes(url): """unfiltered and unranked. Return all disputes we find""" try: htmlcontent = urllib2.urlopen(url,None,2).read(200000) text = html_to_text(htmlcontent) return match_with_claims(text) except: return []
def get_raw_disputes(url):
try:
htmlcontent = urllib2.urlopen(url, None, 2).read(200000)
text = h.html_to_text(htmlcontent)
matches = r.get_sorted_claims(text)
disputes = [dispute for dispute in matches if (dispute[0] > 0)][:4]
unique = []
used = set({})
for dispute in disputes:
if (not dispute[3] in used) and (not dispute[4] in used):
used.add(dispute[3])
used.add(dispute[4])
unique.append(dispute)
return unique
except:
return []
def get_raw_disputes(url):
try:
htmlcontent = urllib2.urlopen(url,None,2).read(200000)
text = h.html_to_text(htmlcontent)
matches = r.get_sorted_claims(text)
disputes = [dispute for dispute in matches if (dispute[0] > 0)][:4]
unique = []
used = set({})
for dispute in disputes:
if (not dispute[3] in used) and (not dispute[4] in used):
used.add(dispute[3])
used.add(dispute[4])
unique.append(dispute)
return unique
except:
return []
def get_page_disputes(url,pages):
try:
htmlcontent = pages[url]
text = h.html_to_text(htmlcontent)
matches = r.get_sorted_claims(text)
disputes = [dispute for dispute in matches if (dispute[0] > 0)][:4]
unique = []
used = set({})
for dispute in disputes:
if (not dispute[3] in used) and (not dispute[4] in used):
used.add(dispute[3])
used.add(dispute[4])
unique.append(dispute)
disputes = [template("disputed_box",dispute = d[1]) for d in unique]
return " ".join(disputes)
except:
return ""
def get_page_disputes(url, pages=None):
try:
if pages:
htmlcontent = pages[url]
else:
htmlcontent = urllib2.urlopen(url, None, 2).read(200000)
text = h.html_to_text(htmlcontent)
matches = r.get_sorted_claims(text)
disputes = [dispute for dispute in matches if (dispute[0] > 0)][:4]
unique = []
used = set({})
for dispute in disputes:
if (not dispute[3] in used) and (not dispute[4] in used):
used.add(dispute[3])
used.add(dispute[4])
unique.append(dispute)
disputes = [template("disputed_box", dispute=d[1]) for d in unique]
return " ".join(disputes)
except:
return ""
def get_prefixes(results,claim): abstracts = [html_to_text(result["abstract"]) for result in results] prefixes = [prefix_for_claim(abstract,claim) for abstract in abstracts] return [prefix for prefix in prefixes if prefix]
def get_abstracts(results,claim): return [html_to_text(result["abstract"]) for result in results]
def get_context(url,matchtext,before,after): html = get_cached_url(url).read() textsegments = html_to_text(html) i = textsegments.find(matchtext) bigtext = textsegments[max(0,i-before):min(i+after,len(textsegments))] return trim_to_words(bigtext)
def claims_from_html(content): text = ht.html_to_text(nt.convert_entities(content)) return claims_from_body(text)
def bodys_from_tab_file(f):
for line in f:
row = line.strip().split("\t")
if len(row) > 3:
yield ht.html_to_text(nt.convert_entities(row[3]))
def get_prefixes(results, claim):
abstracts = [html_to_text(result["abstract"]) for result in results]
prefixes = [prefix_for_claim(abstract, claim) for abstract in abstracts]
return [prefix for prefix in prefixes if prefix]
def bodys_from_tab_file(f):
for line in f:
row = line.strip().split("\t")
if len(row) > 3:
yield ht.html_to_text(nt.convert_entities(row[3]))
def claims_from_html(content):
text = ht.html_to_text(nt.convert_entities(content))
return claims_from_body(text)
def get_abstracts(results, claim):
return [html_to_text(result["abstract"]) for result in results]
