def __init__(self): self.packages = {} self.logger = ourlogging.otherLogger("Package Manager") #load all packages from directory, filter for actual package directories self.allPackNames = [filename for filename in os.listdir('.\\packages\\')] self.allPackNames = filter(lambda x: x[0] == '_' and x[1] != '_', self.allPackNames)
import urllib2 import re import calendar import ourlogging from BeautifulSoup import BeautifulSoup logger = ourlogging.otherLogger("packages.util") def getPage(url): """Returns the contents of a url as a string. This currently doesn't do anything to handle exceptions. @param url The url to grab a page from. @return A string containing the page contents of url. """ try: f = urllib2.urlopen(url) page = f.read() f.close() except urllib2.URLError: logger.warning("Couldn't not connect to and read from %s" % url) except: logger.warning('unknown error running getPage(%s)' % url) raise else: return page def scrapePage(reg, url): """Scrapes the page from url for the reg at position pos.
import urllib2, re, calendar, logging, _winreg, ourlogging, platform from BeautifulSoup import BeautifulSoup logger = ourlogging.otherLogger("packages.util") def getPage(url): """Returns the contents of a url as a string. This currently doesn't do anything to handle exceptions. @param url The url to grab a page from. @return A string containing the page contents of url. """ try: f = urllib2.urlopen(url) page = f.read() f.close() except urllib2.URLError: logger.warning("Couldn't not connect to and read from %s" % url) except: logger.warning('unknown error running getPage(%s)' % url) raise else: return page def scrapePage(reg, url): """Scrapes the page from url for the reg at position pos.