def test_basic():
test_support.requires('network')
from eventlet.green import urllib
if test_support.verbose:
print "test_basic ..."
socket.RAND_status()
socket.RAND_add("this is a random string", 75.0)
try:
f = urllib.urlopen('https://sf.net')
except IOError, exc:
if exc.errno == errno.ETIMEDOUT:
raise test_support.ResourceDenied('HTTPS connection is timing out')
else:
raise
def test_basic():
test_support.requires('network')
from eventlet.green import urllib
if test_support.verbose:
print "test_basic ..."
socket.RAND_status()
socket.RAND_add("this is a random string", 75.0)
try:
f = urllib.urlopen('https://sf.net')
except IOError, exc:
if exc.errno == errno.ETIMEDOUT:
raise test_support.ResourceDenied('HTTPS connection is timing out')
else:
raise
def fetch_html(url):
print "accessing url {0}".format(url)
return urllib.urlopen(url).read()
from bs4 import BeautifulSoup
import json
import eventlet
from eventlet.green import urllib
from scraper.models import publicSkills
manager = publicSkills.objects
coursera_courses_json = json.loads(urllib.urlopen("https://www.coursera.org/maestro/api/topic/list?full=1").read())
coursera_class_base_url = "https://www.coursera.org/course/"
exclusion_list = ['Microsoft Office', 'Microsoft Word', 'PowerPoint', 'Microsoft Excel', 'Photoshop', 'Word', 'Research', 'Teamwork', 'Customer Service', 'Time Management', 'Excel', 'Office', 'MIPS', 'Facebook', 'English', 'Editing', 'Outlook', 'Google Docs', 'Windows'] #skills we don't think are of interest to our users
def get_url_list(xml):
soup = BeautifulSoup(xml)
person_list = soup.find_all("public-profile-url")
url_list = []
for person in person_list:
if person.text != "":
url_list.append(person.text)
return url_list
def get_personal_skills(xml):
soup = BeautifulSoup(xml)
skill_list = soup.find_all("name")
names = [skill.text for skill in skill_list]
return names
def fetch_html(url):
print "accessing url {0}".format(url)
return urllib.urlopen(url).read()
def scrub_html(text):
def getpage(self):
page = urllib.urlopen("http://code.google.com/p/eventlet-pyqt/").read().decode("utf-8")
self.setHtml(page)
def getpage(self):
page = urllib.urlopen(
"http://code.google.com/p/eventlet-pyqt/").read().decode("utf-8")
self.setHtml(page)
def getpage(self):
page = urlopen("http://www.163.com/").read().decode("gbk", "replace")
self.setPlainText(page)
self.operations.kill("print_number")
