def printDanmu(dmlist, av):
filename = "av" + str(av) + ".txt"
print("Loading...\n")
try:
with codecs.open(filename, 'w', "utf-8") as t:
for dm in dmlist:
t.write(dm.string + '\n')
analyse(filename, av)
except Exception, e:
logger.error('Failed to upload to ftp: ' + str(e))
def total_analyse(data, dirname='beifen'):
pl = os.listdir(dirname)
for p in pl:
path = dirname + '\\' + p
f = open(path, 'rb')
scale = pickle.load(f)
f.close()
for i in range(4):
print '* * * * ' * 6
analyse(data, scale, i)
print '* * * * ' * 6
def total_analyse(data,dirname='beifen'):
pl=os.listdir(dirname)
for p in pl:
path=dirname+'\\'+p
f=open(path,'rb')
scale=pickle.load(f)
f.close()
for i in range(4):
print '* * * * '*6
analyse(data,scale,i)
print '* * * * '*6
def main():
# func = input('''
# 1: Calculate password;
# 2: Analyse WeChat message.
# ''')
func = '2'
if func == '1':
IMEI = input('IMEI: ') # 794825438204445
UID = input('UID: ') # -1193869337
password = getPsw(IMEI, UID) # 74ee691
print(password)
elif func == '2':
knownType = checkType()
result = analyse(knownType)
with open('results\\result.json', 'w', encoding='utf8') as j:
json.dump(result, j, ensure_ascii=False)
print('Result.json saved successfully.')
else:
print('Try again.')
main()
def draw_word_cloud(cid_list, name):
'''
绘制词云
:param cid 视频cid编号
:param name 人物名
'''
lst = analyse(cid_list)
words_count_list_TR = lst[0]
words_count_list_TI = lst[1]
word_cloud_TR = (
WordCloud(init_opts=opts.InitOpts(theme=ThemeType.ROMA))
.add("", words_count_list_TR, word_size_range=[20, 50], shape=SymbolType.RECT)
.set_global_opts(title_opts=opts.TitleOpts(title="{}词云TOP50".format(name), subtitle="基于TextRank算法的关键词抽取"))
.render('{}_WordCloud_TR.html'.format(name))
)
word_cloud_TI = (
WordCloud(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
.add("", words_count_list_TI, word_size_range=[20, 100], shape=SymbolType.DIAMOND)
.set_global_opts(title_opts=opts.TitleOpts(title="{}词云TOP50".format(name), subtitle="基于TF-IDF算法的关键词抽取"))
.render('{}_WordCloud_TI.html'.format(name))
)
print('====={}词云绘制完毕====='.format(name))
# coding:utf-8
import jieba
import jieba.analyse
def analyse():
content = open('Readhub.md').read()
tags = jieba.analyse.extract_tags(content,topK=100)
print ' '.join(tags)
if __name__ == '__main__':
analyse()
withWeight=True,
allowPOS=('n'))
# 带词频
for tag in tags:
print(tag[0] + ',' + str(tag[1]))
print('===========================')
# 不带词频，仅用于生成TagCloud的...
for tag in tags:
print(tag[0], end=',')
def get_content(txtdir):
content = []
txts = os.listdir(txtdir)
for each_txt in txts:
with open(txtdir + os.sep + each_txt, mode='rt',
encoding='utf-8') as f:
str = "".join(f.readlines())
content.append(str)
f.close()
return "".join(content)
if __name__ == '__main__':
content_txt = get_content('D:\LagouJobInfo\lagou\details\网络爬虫')
analyse(content_txt,
'C:/Users/XuLu/PycharmProjects/LagouJob/stopwords.txt',
'C:/Users/XuLu/PycharmProjects/LagouJob/userdict.txt')
else:
tongji[u'' + v] = int(n * 10000)
finally:
pass
#要分析多少行数据，在这里写，配合SQL语句使用
for x in range(12, 100000, 100000):
start = time.time()
content = check_state(str(x))
end = time.time()
escape = end - start
print('本次数据库读取时间：' + str(escape))
start = time.time()
analyse(content)
end = time.time()
escape = end - start
print('本次词频提取用时：' + str(escape))
print 'do a work'
#此处也可以直接打印结果
#result = sorted(tongji.items(), key = lambda x: x[1], reverse=True)
#fre = json.dumps(result, ensure_ascii=False, encoding='UTF-8')
#绘制词云图
wordcloud = WordCloud(
font_path="simfang.ttf",
background_color='White').generate_from_frequencies(tongji)
import matplotlib.pyplot as plt
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis("off")
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import jieba
seg_list = jieba.analyse('我来到北京清华大学')
print seg_list
jieba.load_userdict(userdictpath)
# 加载停用词
jieba.analyse.set_stop_words(stopwordspath)
tags = jieba.analyse.extract_tags(strcontent, topK=20, withWeight=True, allowPOS=('n'))
# 带词频
for tag in tags:
print(tag[0] + ',' + str(tag[1]))
print('===========================')
# 不带词频，仅用于生成TagCloud的...
for tag in tags:
print(tag[0], end=',')
def get_content(txtdir):
content = []
txts = os.listdir(txtdir)
for each_txt in txts:
with open(txtdir + os.sep + each_txt, mode='rt', encoding='utf-8') as f:
str = "".join(f.readlines())
content.append(str)
f.close()
return "".join(content)
if __name__ == '__main__':
content_txt = get_content('D:/LagouJobInfo/lagou/details/计算机视觉')
analyse(content_txt, 'D:/Users/LucasX/PycharmProjects/LagouJob/stopwords.txt',
'D:/Users/LucasX/PycharmProjects/LagouJob/userdict.txt')
tags = jieba.analyse.extract_tags(strcontent, topK=20, withWeight=True, allowPOS=("n"))
# 带词频
for tag in tags:
print(tag[0] + " : " + str(tag[1]))
print("===========================")
# 不带词频，仅用于生成TagCloud的...
for tag in tags:
print(tag[0], end=",")
def get_content(txtdir):
content = []
txts = os.listdir(txtdir)
for each_txt in txts:
with open(txtdir + os.sep + each_txt, mode="rt", encoding="utf-8") as f:
str = "".join(f.readlines())
content.append(str)
f.close()
return "".join(content)
if __name__ == "__main__":
content_txt = get_content("D:/datamining")
analyse(
content_txt,
"C:/Users/XuLu/PycharmProjects/LagouJob/stopwords.txt",
"C:/Users/XuLu/PycharmProjects/LagouJob/userdict.txt",
)
