# -*- coding: utf-8 -*-import requests
import re
import os
import codecsdef get_title(url):s = requests.session()h = s.get(url)html = h.content.decode('utf-8')#print html
qurl = r'<a href="forum.*? class="s xst">(.*?)</a>'qurllist = re.findall(qurl,html)#print qurllistfor each in qurllist:f = codecs.open("result.txt", 'a', 'utf-8')f.write(each+'\n')print each#f.flush()
        f.close()for i in range(1,1000):url = 'http://rs.xidian.edu.cn/forum.php?mod=forumdisplay&fid=72&page='+str(i)get_title(url)

import sys
sys.path.append('../')import jieba
import jieba.analyse
from optparse import OptionParserUSAGE = "usage:    python extract_tags_with_weight.py [file name] -k [top k] -w [with weight=1 or 0]"parser = OptionParser(USAGE)
parser.add_option("-k", dest="topK")
parser.add_option("-w", dest="withWeight")
opt, args = parser.parse_args()if len(args) < 1:print(USAGE)sys.exit(1)file_name = args[0]if opt.topK is None:topK = 10
else:topK = int(opt.topK)if opt.withWeight is None:withWeight = False
else:if int(opt.withWeight) is 1:withWeight = Trueelse:withWeight = Falsecontent = open(file_name, 'rb').read()tags = jieba.analyse.extract_tags(content, topK=topK, withWeight=withWeight)if withWeight is True:for tag in tags:print("tag: %s\t\t weight: %f" % (tag[0],tag[1]))
else:print(",".join(tags))

python extract_tags_with_weight.py [file name] -k [top k] -w [with weight=1 or 0]

# -*- coding: utf-8 -*-
import codecs
import random
from pytagcloud import create_tag_image, create_html_data, make_tags, \LAYOUT_HORIZONTAL, LAYOUTS
from pytagcloud.colors import COLOR_SCHEMES
from pytagcloud.lang.counter import get_tag_countswd = {}fp=codecs.open("rsa.txt", "r",'utf-8');alllines=fp.readlines();fp.close();for eachline in alllines:line = eachline.split('        ')#print eachline,wd[line[0]] = int(line[1])
print wdfrom operator import itemgetter
swd = sorted(wd.iteritems(), key=itemgetter(1), reverse=True)
tags = make_tags(swd,minsize = 50, maxsize = 240,colors=random.choice(COLOR_SCHEMES.values()))
create_tag_image(tags, 'keyword_tag_cloud4.png', background=(0, 0, 0, 255),
size=(2400, 1000),layout=LAYOUT_HORIZONTAL,
fontname="SimHei")