def parse(self, response):
# self.store_html(response)
for item in self.parse_tables(response):
yield item
links = Selector(response).xpath("//a/@href").extract()
for l in links:
normLink = Utility.normalize(response.url, l)
yield Request(normLink, callback=self.follow_links)
def follow_links(self, response):
if next(self.table_counter) > self.table_limit:
raise CloseSpider(reason="Enough tables")
# self.store_html(response)
for item in self.parse_tables(response):
yield item
links = Selector(response).xpath("//a/@href").extract()
for l in links:
normLink = Utility.normalize(response.url, l)
yield Request(normLink, callback=self.follow_links)
def main():
# crawlerdb example
# db = load_db("../data/crawlerdb")
# print 'DB at first run'
# db.display()
# db.add_one_html()
# db.add_n_tables(100)
# db.display()
# print 'saving database...'
# save_db(db, "../data/crawlerdb")
# print 'load database...'
# db2 = load_db("../data/crawlerdb")
# db2.display()
"""
A program to generate seeds file for the web crawler.
"""
parser = argparse.ArgumentParser()
parser.add_argument("-r", "--rootdir", type=str,
help="path to root directory")
parser.add_argument("-c", "--countries", type=str,
help="a file contains country list")
parser.add_argument("-t", "--transports", type=str,
help="a file contains transportation mode")
parser.add_argument("-s", "--seeds", type=str,
help="a file contains seed")
parser.add_argument("-l", "--loglevel", type=str, help="set logging level")
args = parser.parse_args()
if args.loglevel:
numeric_level = getattr(logging, args.loglevel.upper(), None)
if not isinstance(numeric_level, int):
raise ValueError('Invalid log level: %s' % args.loglevel)
logging.basicConfig(level=numeric_level)
countries = args.rootdir + '/' + args.countries
transports = args.rootdir + '/' + args.transports
seeds = args.rootdir + '/' + args.seeds
Utility.generate_seeds(countries, transports, seeds)
