return found
found_books = set()
prev = ''
for filename in (i for i in os.listdir(arc_dir) if i.endswith('.arc')):
if not filename.startswith('20100412'):
continue
for url, wire in read_arc(arc_dir + '/' + filename):
#print filename, url
if url.startswith('file'):
continue
if not url.startswith('http://www.amazon.com/s?'):
continue
body = read_body(wire)
m = re_title.search(body)
if m.group(1) != prev:
print(m.group(1))
prev = m.group(1)
continue
doc = fromstring(body)
try:
doc.get_element_by_id('noResultsTitle')
continue
except KeyError:
pass
rc = doc.find_class('resultCount')
if rc:
m = re_result_count.match(rc[0].text)
if m:
found.append(m.group(1))
return found
found_books = set()
prev = ''
for filename in (i for i in os.listdir(arc_dir) if i.endswith('.arc')):
if not filename.startswith('20100412'):
continue
for url, wire in read_arc(arc_dir +'/' + filename):
#print filename, url
if url.startswith('file'):
continue
if not url.startswith('http://www.amazon.com/s?'):
continue
body = read_body(wire)
m = re_title.search(body)
if m.group(1) != prev:
print(m.group(1))
prev = m.group(1)
continue
doc = fromstring(body)
try:
doc.get_element_by_id('noResultsTitle')
continue
except KeyError:
pass
rc = doc.find_class('resultCount')
if rc:
m = re_result_count.match(rc[0].text)
if m: