对《还珠格格》进行词频统计
对《还珠格格》的词频统计生成词云标签
将《2016年中国政府工作报告》变成词云是这样的
然后是《小时代》
以小燕子照片为词云背景
对《射雕英雄传》进行词频统计并以郭靖剧照作为词云背景
有没有满满的即视感？
一个Web端的电影数据库交互
可以了解整个中国香港电影史，从早期合拍上海片，到胡金栓的武侠片，到李小龙时代，然后是成龙，接着周星驰
对职责要求的词频分析，提炼出必需技能
用爬虫爬下上万知乎女神照片
最后，展示一下Python代码：
词频统计和词云的代码
代码语言：javascript复制
from wordcloud import WordCloud
import jieba
import PIL
import matplotlib.pyplot as plt
import numpy as np
def wordcloudplot(txt):
path = 'd:/jieba/msyh.ttf'
path = unicode(path, 'utf8').encode('gb18030')
alice_mask = np.array(PIL.Image.open('d:/jieba/she.jpg'))
wordcloud = WordCloud(font_path=path, background_color="white", margin=5, width=1800, height=800, mask=alice_mask, max_words=2000, max_font_size=60, random_state=42)
wordcloud = wordcloud.generate(txt)
wordcloud.to_file('d:/jieba/she2.jpg')
plt.imshow(wordcloud)
plt.axis("off")
plt.show()
def main():
a = []
f = open(r'd:jiebabookshe.txt', 'r').read()
words = list(jieba.cut(f))
for word in words:
if len(word) > 1:
a.append(word)
txt = r' '.join(a)
wordcloudplot(txt)
if __name__ == '__main__':
main()
爬知乎女神的代码
代码语言：javascript复制
import requests
import urllib
import re
import random
from time import sleep
def main():
url = 'xxx'
headers = {xxx}
i = 925
for x in xrange(1020, 2000, 20):
data = {'start': '1000',
'offset': str(x),
'_xsrf': 'a128464ef225a69348cef94c38f4e428'}
content = requests.post(url, headers=headers, data=data, timeout=10).text
imgs = re.findall('<img src=\\"(.*?)_m.jpg', content)
for img in imgs:
try:
img = img.replace('\', '')
pic = img '.jpg'
path = 'd:\bs4\zhihu\jpg4\' str(i) '.jpg'
urllib.urlretrieve(pic, path)
print ('下载了第' str(i) u'张图片')
i = 1
sleep(random.uniform(0.5, 1))
except:
print ('抓漏1张')
pass
sleep(random.uniform(0.5, 1))
if __name__ == '__main__':
main()
来源：挖数
链接：https://www.zhihu.com/question/28975391
