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 ""
