#!/usr/bin/env python
from parser import DmozParser
from handlers import JSONWriter
class LawrenceFilter:
def __init__(self):
self._file = open("seeds.txt", 'w')
def page(self, page, content):
if page != None and page != "":
topic = content['topic']
if topic.find('United_States/Kansas/Localities/L/Lawrence') > 0 :
self._file.write(page + "\n")
print "found page %s in topic %s" % (page , topic)
def finish(self):
self._file.close()
parser = DmozParser()
parser.add_handler(
LawrenceFilter()
#JSONWriter('output.json')
)
parser.run()
#!/usr/bin/env python
from parser import DmozParser
from handlers import JSONWriter
parser = DmozParser()
parser.add_handler(JSONWriter('output.json'))
parser.run()
# <d:Title>Animation World Network</d:Title>
# <d:Description>Provides information resources to the international animation community. Features include searchable database archives, monthly magazine, web animation guide, the Animation Village, discussion forums and other useful resources.</d:Description>
# <priority>1</priority>
# <topic>Top/Arts/Animation</topic>
# </ExternalPage>
# This assumption is strictly checked, and processing will abort if it is violated.
# To use this parser, one should unpack the content.rdf.u8.gz first
class Filter:
def __init__(self):
self._file = open("seeds.txt", 'w')
def page(self, page, content):
if page != None and page != "":
topic = content['topic']
with open("category.txt") as f:
ctg = f.readline().strip()
if topic.find(ctg) > 0 :
self._file.write(page + "\n")
print "found page %s in topic %s" % (page , topic)
def finish(self):
self._file.close()
parser = DmozParser()
parser.add_handler(
Filter()
)
parser.run()
# <ExternalPage about="http://www.awn.com/">
# <d:Title>Animation World Network</d:Title>
# <d:Description>Provides information resources to the international animation community. Features include searchable database archives, monthly magazine, web animation guide, the Animation Village, discussion forums and other useful resources.</d:Description>
# <priority>1</priority>
# <topic>Top/Arts/Animation</topic>
# </ExternalPage>
# This assumption is strictly checked, and processing will abort if it is violated.
# To use this parser, one should unpack the content.rdf.u8.gz first
class Filter:
def __init__(self):
self._file = open("seeds.txt", 'w')
def page(self, page, content):
if page != None and page != "":
topic = content['topic']
with open("category.txt") as f:
ctg = f.readline().strip()
if topic.find(ctg) > 0:
self._file.write(page + "\n")
print "found page %s in topic %s" % (page, topic)
def finish(self):
self._file.close()
parser = DmozParser()
parser.add_handler(Filter())
parser.run()
#!/usr/bin/env python
from parser import DmozParser
from handlers import JSONWriter
class LawrenceFilter:
def __init__(self):
self._file = open("seeds.txt", 'w')
def page(self, page, content):
if page != None and page != "":
topic = content['topic']
if topic.find('Venture') > 0 or topic.find(
'Financial_Services') > 0:
self._file.write(page + " " + topic + "\n")
print("found page %s in topic %s" % (page, topic))
def finish(self):
self._file.close()
parser = DmozParser()
parser.add_handler(LawrenceFilter()
#JSONWriter('output.json')
)
parser.run()
#!/usr/bin/env python
import logging
from parser import DmozParser
from handlers import JSONWriter
from handlers import TaxonomieWriter
logger = logging.getLogger(__name__)
logging.basicConfig(
format='%(asctime)s : %(levelname)s : %(module)s:%(funcName)s:%(lineno)d : %(message)s',
level=logging.INFO)
parser = DmozParser()
parser.input_path = '../content.rdf.u8.gz'
parser.add_handler(TaxonomieWriter('output.json'))
parser.run()