def test_map(self):
def _square(x):
return x + 1
numbers = range(1000)
squared_numbers = map(_square, numbers)
results = parallel_map(_square, numbers, 500)
self.assertTrue(results == squared_numbers)
def test_map(self):
def _square(x):
return x + 1
numbers = range(1000)
squared_numbers = map(_square, numbers)
results = parallel_map(_square, numbers, 500)
self.assertTrue(results == squared_numbers)
def getlinks(self, query, numlinks=5, size=(100, 1500)):
start = datetime.now()
query = query.replace(" ", "+")
url = self._LIST_URL.format(query=query, sizefrom=size[0], sizeto=size[1])
urls = [url.format(pageid=i) for i in range(1, self._NUM_PAGES_SCRAPED + 1)]
links = parallel_map(self._scrapepage, urls)
res = []
for link in links:
res += link
links = filter(lambda x: x is not None, res)
stop = datetime.now()
logger.debug("getlinks took: {time}".format(time=stop - start))
return links[:numlinks]
def _getfilehostlinks(self, url):
logger.debug("_getfilehostlinks")
response = self._getresponse(url)
if not response:
return None
html = response.text
logger.debug("Getting filehost links")
doc = lxml.html.fromstring(html)
try:
links = doc.cssselect("pre#copy_paste_links")[0].text_content().strip("\"").strip().split()
title = doc.cssselect("div.file-heading h1")[0].text_content()
except IndexError:
logger.debug("div.dotter.h1 doesn't exist. Skipping..")
return None
uris = parallel_map(self._validate, links)
if None in uris:
return None
title = title[:-9] # remove " download" from end of title
return Link(title=title, uris=uris)
def _scrapepage(self, url):
logger.debug("_scrapepage")
response = self._getresponse(url)
if not response:
print("ERROR: Couldn't connect to filestube!")
return []
html = response.text
doc = lxml.html.fromstring(html)
results = doc.cssselect("div.newresult")
links = []
for result in results:
try:
a_tag = result.cssselect("a.resultsLink")[0]
link = self._BASE_URL + a_tag.get('href')
links.append(link)
except IndexError:
print("there was no link on the page")
continue
logger.debug("Number of links: {numlinks}".format(numlinks=len(links)))
return parallel_map(self._getfilehostlinks, links)
