python网页回帖统计_Python爬取52论坛指定帖子回复数据生成词云图

[Python] 纯文本查看 复制代码import requests

from lxml import etree

import jieba

import numpy as np

import matplotlib.pyplot as plt

import time

from PIL import Image

from wordcloud import WordCloud, ImageColorGenerator

def GetData(url):

html = requests.get(url)

ehtml = etree.HTML(html.text)

pagenum = ehtml.xpath('//*[@class="last"]/text()')

if len(pagenum)>0:

txt=''

pagenum = pagenum[1].replace('... ', '')

print('回复共 ' + str(pagenum) + ' 页,请稍候...')

url=url.split('-')

for i in range(1,int(pagenum)+1):

print('第 '+str(i)+' 页')

nurl=url[0]+'-'+url[1]+'-'+str(i)+'-'+url[3]

html = requests.get(nurl)

ehtml = etree.HTML(html.text)

pltxt = ''.join(ehtml.xpath('//*[@class="t_f"]/text()'))

txt = txt + pltxt

time.sleep(1) # 给服务器留些喘气的时间

else:

print('回复只有 1 页,这数据是不是太少了...')

txt = ''.join(ehtml.xpath('//*[@class="t_f"]/text()'))

cut_text =txt

background_image = np.array(Image.open('c:\\bg.jpg'))

wordcloud = WordCloud(

font_path="C:/Windows/Fonts/simfang.ttf",

background_color="white",

mask=background_image).generate(cut_text)

image_colors = ImageColorGenerator(background_image)

plt.imshow(wordcloud.recolor(color_func=image_colors), interpolation="bilinear")

plt.axis("off")

plt.show()

if __name__ == '__main__':

print('开始获取,请稍候...')

url='https://www.52pojie.cn/thread-924213-1-1.html'

GetData(url)