#! /usr/bin/python
# -*- coding: utf-8 -*-
from BeautifulSoup import BeautifulSoup
import db_wrapper
import scrape_mike as ssm
url = "http://www.canadianwebradio.com/"
soup = ssm.get_page(url)
countries = soup.find("table", {"id" : "thetable"})
db_wrapper.connect()
# Get every countries's page
for row in countries.findAll('tr'):
link = row.findAll('td')[0].findAll('a')[0]
soup = ssm.get_page(url + link['href'])
data = soup.find("table", {"id" : "thetable3"})
ssm.scrape(
data,
name_td_id=0, location_td_id=2, stream_td_id=4, categ_td_id=5,
country="Canada")
db_wrapper.disconnect()
#! /usr/bin/python
# -*- coding: utf-8 -*-
from BeautifulSoup import BeautifulSoup
import db_wrapper
import scrape_mike as ssm
db_wrapper.connect()
url = "http://www.usliveradio.com/"
soup = ssm.get_page(url)
data = soup.find("table", {"id": "thetable3"})
ssm.scrape(data,
name_td_id=0,
location_td_id=1,
stream_td_id=4,
categ_td_id=5,
country="US")
db_wrapper.disconnect()
"Uruguay",
"Uzbekistan",
"Vanuatu",
"Vatican City",
"Venezuela",
"Vietnam",
"Wallis-Futuna Islands",
"Western Sahara",
"Yemen",
"Zambia",
"Zimbabwe"
]
db_wrapper.connect()
soup = ssm.get_page("http://www.listenlive.eu/index.html")
countries = soup.find("table", {"id" : "thetable"})
for row in countries.findAll('tr'):
link = row.findAll('td')[0].findAll('a')[0]
country_name = link.text
found = False
if "Vatican State" in country_name:
country_name = "Vatican City"
for cnt in COUNTRIES:
if cnt in country_name:
found = True
if found == False:
print "Country (%s) not found in list. Moving on." % country_name
sys.exit(0)