def initialize_user_dict(tag, count=5): user_dict = {} # get the top count' posts for p1 in get_tagposts(tag=tag)[0:count]: # find all users who posted this for p2 in get_urlposts(p1['url']): user = p2['user'] user_dict[user] = {} return user_dict
def fill_items(self): all_items = dict() for object in self.object_dict: for i in range(3): try: posts = get_tagposts(object) break except: print "Failed tag "+object+", retrying" time.sleep(4) for post in posts: url = post['url'] self.object_dict[object][url]=post['tags'].lower().split()
def build_tag_list(tag, n=20): """ Given a tag, fetches more tags by crawling for tags. Returns the tags. """ unprocessed_tags = [tag] processed_tags = [] while len(unprocessed_tags) > 0 and len(unprocessed_tags) + len(processed_tags) < n: next_tag = unprocessed_tags.pop() bookmarks = get_tagposts(next_tag) processed_tags.append(next_tag) for bookmark in bookmarks: for tag in bookmark["tags"]: if tag not in processed_tags and tag not in unprocessed_tags: unprocessed_tags.append(tag) return (unprocessed_tags + processed_tags)[-n:]
def initializeUserDict(tag, count=5, cache_dict=True): #get_popular doesn't work any more. Getting by tag #return [url_post['user'] for item in get_tagposts(tag=tag)[0:count] for url_post in get_urlposts(item['url'])] #from hashlib import md5 #print md5('http://usingtechnologybetter.com/chrome-extensions-for-teachers/').hexdigest() user_dict_cache_file = "user_dict.p" if cache_dict and exists(user_dict_cache_file): print "Reading the user_dict from cache file", user_dict_cache_file cache_file = open(user_dict_cache_file, "rb") user_dict = load(cache_file) cache_file.close() else: user_dict = dict([(url_info['user'], {}) for item in get_tagposts(tag=tag)[0:count] for url_info in get_urlposts(item['url']) if url_info['user'] != '']) if cache_dict: print "Writing the user_dict to cache file", user_dict_cache_file cache_file = open(user_dict_cache_file, "wb") dump(user_dict, cache_file) cache_file.close() return user_dict
def initializeUserDict(tag, count=5, cache_dict = True): #get_popular doesn't work any more. Getting by tag #return [url_post['user'] for item in get_tagposts(tag=tag)[0:count] for url_post in get_urlposts(item['url'])] #from hashlib import md5 #print md5('http://usingtechnologybetter.com/chrome-extensions-for-teachers/').hexdigest() user_dict_cache_file = "user_dict.p" if cache_dict and exists(user_dict_cache_file): print "Reading the user_dict from cache file", user_dict_cache_file cache_file = open(user_dict_cache_file, "rb") user_dict = load(cache_file) cache_file.close() else: user_dict = dict( [(url_info['user'], {}) for item in get_tagposts(tag=tag)[0:count] for url_info in get_urlposts(item['url']) if url_info['user'] != ''] ) if cache_dict: print "Writing the user_dict to cache file", user_dict_cache_file cache_file = open(user_dict_cache_file, "wb") dump(user_dict, cache_file) cache_file.close() return user_dict
r.append(result) result = p.getrss(tag="python ajax", popular=1) r.append(result) result = p.getrss(tag="python", user="******") r.append(result) result = p.getrss(user="******") r.append(result) result = p.getrss(tag="python ajax", user="******") r.append(result) result = p.getrss() r.append(result) result = p.getrss(url="http://www.heise.de/") r.append(result) result = p.get_userposts("delpy") r.append(result) result = p.get_tagposts("python") r.append(result) result = p.get_urlposts("http://www.heise.de/") r.append(result) result = p.get_popular() r.append(result) result = p.get_popular(tag="python") r.append(result) for i in range(len(r)): if r[i].bozo == 1: print "Catched a exception" print i print r[i]["debug"] print "Exception", r[i].bozo_exception print dir(r[i].bozo_exception)