python中文热词统计demo

背景

老人家不识字，在城市生活不便，喜欢去基督教堂，但是听不懂，也难以和姊妹们(老头老太太们)交流。于是想教他识字，从哪里教起呢，不如从 《圣经》的常用字词开始吧，于是花了几分钟把《圣经》热词统计了一下，代码如下。

代码

# 从 网上下载圣经文字版本： https://drive.my-elibrary.com/%E8%97%8F%E4%B9%A6%E5%85%A5%E5%8F%A3/%E7%B3%BB%E7%BB%9F/%E5%9C%A3%E7%BB%8F%E7%89%88%E6%9C%AC%20%20%20%E4%B8%8E%20%20%20%E5%9C%A3%E7%BB%8F%E7%A0%94%E8%AF%BB/sj/

# 安装jieba分词： pip install jieba
import jieba

sj = open("/Users/xxxx/Downloads/sj.txt")
hotwds = open("/Users/xxxx/hotwds.txt", "w+")

counts = {}
stop_words = [' ', '\u3000', '“', '”', "，","。",", ", '. ',':',': ','：','；','、',';','; ','的','1','2','3','4','5','6','7','8','9','0','\n','‘','！', '’', '（','）','？']
count = 0

line = sj.readline()
while line:
    count = count + 1
    # if count > 10000:
    #     break
    
    words = jieba.lcut(line)
    # print(words)
    for word in words:
        if word in stop_words:
            continue
        # print(word)
        counts[word] = counts.get(word,0) + 1
    line = sj.readline()

print(count)

items = list(counts.items())
items.sort(key = lambda x:x[1],reverse = True)
print(len(counts.keys()))

res = ""
# 取出排名前200并打印
for i in range(200):
    word,count = items[i]
    res = res + word + ",  "
    print("{0:<10}{1:>5}".format(word,count))

hotwds.write(res)
hotwds.close()

附200热词表: