def parsebloglinks (self, addonlyenglish = False):
self.bloglist = []
leadingblogbrtags = self.soup.findAll('br', {'class':"blog-spacer"})
for leadingblogbr in leadingblogbrtags:
summary = leadingblogbr.nextSibling
if type(summary) is BeautifulSoup.NavigableString:
if addonlyenglish and Util.istextenglish(summary) == False:
continue
relativeurl = leadingblogbr.nextSibling.nextSibling['href']
self.bloglist.append('http://www.travelblog.org' + relativeurl)
return self.bloglist
def isvalidforindex(self):
return self.isafrica and Util.istextenglish(self.blog.body) and len(self.blog.body) > 50
import ElasticMappings
import TravelPodParser
import Util
import LoggerConfig
import logging
from elasticsearch import Elasticsearch
logger = logging.getLogger(__name__)
response = ElasticMappings.Blog.search()[0:3500].execute()
count = 0
for blog in response:
if Util.istextenglish(blog.body) == False:
blog.delete()
count+=1
logger.info("Deleted {0} foreign blogs".format(count))
def parsebloglinks (self):
self.bloglist = []
for div in self.soup.findAll('div', attrs={'class':re.compile('^blog_info$')}):
if (Util.istextenglish(div.findAll('p')[1].text)):
self.bloglist.append(div.findNext ('a')['href']);
return self.bloglist
