python爬虫：快到情人节啦，做些爱心图片

爬虫代码：

#encoding=utf-8
import requests
from bs4 import BeautifulSoup
import time
import random

urls = ['https://www.duanwenxue.com/huayu/tianyanmiyu/list_{}.html'.format(str(i)) for i in range(1,50)]

def get_one_page(url):
    resp = requests.get(url)
    if resp.status_code == 200:
        soup = BeautifulSoup(resp.text,'lxml')
        phases = soup.select('body > div.row.inner-row > div.row-left > div.list-short-article > ul > li > p > a')
        with open(u'C:\\Users\Administrator\Desktop\sweet_words.txt', 'wb') as f:
            for phase in phases:
                data = phase.get_text()
                print(data)
                f.write(data.encode('utf-8'))
    else:
        print('not found')

if __name__ == '__main__':
    for url in urls:
        get_one_page(url)
        time.sleep(random.randint(2,10))
        print('ok')

分词及词云

import jieba 
import numpy as np
import codecs
import pandas
import matplotlib.pyplot as plt 
from scipy.misc import imread
from wordcloud import WordCloud,ImageColorGenerator

#分词
file=codecs.open(u"C:\\Users\Administrator\Desktop\sweet_words.txt",'r',encoding='UTF-8')
content=file.read()
file.close()
segment=[]
#jiaba调用了自己的分词算法，将切分好的文本按逗号分隔符分开
segs=jieba.cut(content)
for seg in segs:
    if len(seg)>1 and seg!='\r\n':
        segment.append(seg)

#统计分词结果
words_df=pandas.DataFrame({'segment':segment})#组建数据框pandas.DataFrame
words_df.head()
words_stat=words_df.groupby(by=['segment'])['segment'].agg({"计数":np.size})
words_stat=words_stat.reset_index()
words_stat

%matplotlib
#生成一个matplot对象，传入一个字体位置的路径和背景颜色即可
wordcloud=WordCloud(font_path="C:\simhei.ttf",background_color="white",max_words=200)
#WordCloud方法接受一个字典结构的输入，我们前面整理出来的词频统计结果是数据框的形式，因此需要转换，转换的方法，
#首先把分词设置为数据框的索引，然后在调用一个to_dict()的方法，就可以转换为字典的机构
words=words_stat.set_index('segment').to_dict()
#接着调用fit_words方法来调用我们的词频
wordcloud.fit_words(words['计数'])
#绘图
plt.imshow(wordcloud)
plt.show()

不同字体网上都能搜到，桃心图片是用ps裁剪的，一定要是桃心形状，而不是方形的图片