def testGetTextsFromCulinaria(self):
from TextsCrawler import Parser
pars = Parser()
texts = pars.getTextsFromCulinaria("http://feeds2.feedburner.com/CulinariaEReceitas")
for text in texts:
print "---------------------------------------------------"
print "title:", text
print "text:", texts[text]
def testGetTextsFromArtigosCom(self):
from TextsCrawler import Parser
pars = Parser()
texts = pars.getTextsFromArtigosCom("http://www.artigos.com/option,com_mtree/task,rss/type,new/Itemid,61/")
for text in texts:
print "---------------------------------------------------"
print "title:", text
print "text:", texts[text]
def testGetTextWebArtigo(self):
from TextsCrawler import Parser
pars = Parser()
texts = pars.getTextWebArtigo("http://www.webartigos.com/articlerss/cat/17/")
for text in texts:
print "---------------------------------------------------"
print "title:", text
print "text:", texts[text]
def testGetHTML(self):
from TextsCrawler import Parser
pars = Parser()
html = pars._getHTML("http://perdu.com")
self.assertEqual(
html,
"<html><head><title>Vous Etes Perdu ?</title></head><body><h1>Perdu sur l'Internet ?</h1><h2>Pas de panique, on va vous aider</h2><strong><pre> * <----- vous êtes ici</pre></strong></body></html>\n",
)
def testGetTextsFromCrondia(self):
from TextsCrawler import Parser
pars = Parser()
texts = pars.getTextsFromCrondia("http://crondia.blogspot.com/feeds/posts/default?alt=rss")
for text in texts:
print "---------------------------------------------------"
print "title:", text
print "text:", texts[text]
def testGetTextsFromUOL(self):
from TextsCrawler import Parser
pars = Parser()
texts = pars.getTextsFromUOL("http://feeds.folha.uol.com.br/esporte/rss091.xml")
for text in texts:
print "---------------------------------------------------"
print "title:", text
print "text:", texts[text]
def testGetTextsFromGlobo(self):
from TextsCrawler import Parser
pars = Parser()
texts = pars.getTextsFromGlobo("http://oglobo.globo.com/rss/plantao.xml")
for text in texts:
print "---------------------------------------------------"
print "title:", text
print "text:", texts[text]
def testGetTextsHoroscopo(self):
from TextsCrawler import Parser
pars = Parser()
texts = pars.getTextsHoroscopo("http://www.jornaldelondrina.com.br/horoscopo/")
for text in texts:
print "---------------------------------------------------"
print "title:", text
print "text:", texts[text]
def testGetTextsArtigonal(self):
from TextsCrawler import Parser
pars = Parser()
texts = pars.getTextsFromArtigonal("http://www.artigonal.com/rss/")
for text in texts:
print "---------------------------------------------------"
print "title:", text
print "text:", texts[text]
def testGetTextsFromartigosEtc(self):
from TextsCrawler import Parser
pars = Parser()
texts = pars.getTextsFromArtigosEtc("http://www.artigos.etc.br/feed")
for text in texts:
print "---------------------------------------------------"
print "title:", text
print "text:", texts[text]
def testhtml2text(self):
from TextsCrawler import Parser
pars = Parser()
text = pars._html2text("œ")
def testGetLinks(self):
from TextsCrawler import Parser
pars = Parser()
links = pars._getLinks("http://feedparser.org/docs/examples/atom10.xml")
self.assertEqual(links, {u"First entry title": u"http://example.org/entry/3"})
