1.  urllst = []  2.  titlelst = []  3.  out2 = open('新闻.txt','a',encoding='utf-8')  4.  with open (r'E:pyguanzhuangbingducctvCCTV新闻.txt','r',encoding='utf-8') as f:  5.      text = f.readlines()  6.      for line in text:  7.          title = re.findall('"title":"(.+?)"',line)  8.          url = re.findall(r'http://(.+?).shtml"',line)  9.          if url:  10.              urllst.append(url)  11.      #print(urllst)  12.    13.      for i in range(len(urllst)):  14.          for w in urllst[i]:  15.              url = 'http://'+ w + '.shtml'  16.              print(url)  17.              titlelst.append(url)  

1.  #-*- coding:utf-8 -*-  2.  import requests  3.  import re  4.  from bs4 import BeautifulSoup  5.    6.  urllst = []  7.  titlelst = []  8.  out2 = open('新闻.txt','a',encoding='utf-8')  9.  with open (r'E:pyguanzhuangbingducctvCCTV新闻.txt','r',encoding='utf-8') as f:  10.      text = f.readlines()  11.      for line in text:  12.          title = re.findall('"title":"(.+?)"',line)  13.          url = re.findall(r'http://(.+?).shtml"',line)  14.          if url:  15.              urllst.append(url)  16.      #print(urllst)  17.    18.      for i in range(len(urllst)):  19.          for w in urllst[i]:  20.              url = 'http://'+ w + '.shtml'  21.              #print(url)  22.              titlelst.append(url)  23.      for urll in titlelst:  24.          #print(urll)  25.          try:  26.              r=requests.get(urll)  27.              r.encoding = r.apparent_encoding  28.              r.raise_for_status  29.              print(r.text)  30.              soup = BeautifulSoup(r.text,'lxml')  31.              div = soup.find_all('div',class_="content_area")  32.              soup2 = BeautifulSoup(str(div),'lxml')  33.              p = soup2.find_all('p')  34.              contents = re.findall('[^<p></p>]',str(p))  35.              print(''.join(contents))  36.              print(''.join(contents),file = out2 )  37.          except:  38.              print('失败')

1.  # -*- coding: utf-8 -*-  2.  import jieba  3.  import jieba.posseg as pseg  4.  # 创建停用词list  5.  def stopwordslist(filepath):  6.      stopwords = [line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()]  7.      return stopwords  8.  # 对句子进行分词  9.  def seg_sentence(sentence):  10.      jieba.load_userdict('字典.txt')   11.      #jieba.analyse.set_stop_words('changan_stopwords.txt')  12.      sentence_seged =pseg.cut(sentence.strip())  13.      sentence_seged = jieba.cut(sentence.strip(),cut_all=False)  14.      stopwords = stopwordslist('最全中文停用词.txt')  # 这里加载停用词的路径  15.      outstr = ''  16.      for word in sentence_seged:  17.          if word not in stopwords:  18.              if word != 't':  19.                  outstr += word  20.                  outstr += " "  21.      return outstr  22.  inputs = open('新闻.txt', 'r', encoding='utf-8') # 这里加载分词后文本的路径  23.  outputs = open('新闻_分词去停用词.txt', 'w',encoding='utf-8')  # 这里加载输出文本的路径  24.  for line in inputs:  25.      line_seg = seg_sentence(line)  # 这里的返回值是字符串  26.      outputs.write(line_seg + 'n')  27.  outputs.close()  28.  inputs.close()  29.  print('success')

1.  def random_color_func(word=None, font_size=None, position=None,  orientation=None, font_path=None, random_state=None):  2.      h = random.randint(330,360)  3.      s = int(100.0 * float(random.randint(40, 200)) / 255.0)  4.      l = int(100.0 * float(random.randint(20, 150)) / 255.0)  5.      return "hsl({}, {}%, {}%)".format(h, s, l)

1.  mask= imread('中国地图.png')  2.  wc = WordCloud(font_path=font_path2,  # 设置字体                3.                 background_color=None, mode="RGBA",  # 背景颜色  4.                 max_words=500,  # 词云显示的最大词数  5.                 mask=mask,  # 设置遮罩  6.                 max_font_size=130 ,   # 最大字号7.                 random_state=40,  8.                 font_step= 1,  9.                 min_font_size=16,  10.                 collocations=False,  11.                 color_func = random_color_func)   12.  wc.generate(text)13.  wc.to_file("temp.png")

1.  # -*- coding: utf-8 -*-  2.  #!/usr/bin/env python  3.  import collections  4.  from os import path  5.  from PIL import Image  6.  import numpy as np  7.  import matplotlib.pyplot as plt  8.  from scipy.misc import imread  9.  from wordcloud import WordCloud,ImageColorGenerator  10.  import random  11.  d = path.dirname(__file__)  12.  font_path2='121.TTF'  13.  # 读取整个文本.  14.  text = open('新闻处理_分词去停用词.txt','r',encoding= 'utf-8').read()  15.    16.  def random_color_func(word=None, font_size=None, position=None,  orientation=None, font_path=None, random_state=None):  17.      h  = random.randint(330,360)  18.      s = int(100.0 * float(random.randint(40, 200)) / 255.0)  19.      l = int(100.0 * float(random.randint(20, 150)) / 255.0)  20.      return "hsl({}, {}%, {}%)".format(h, s, l)  21.    22.  mask= imread('中国地图2.png')  23.  wc = WordCloud(font_path=font_path2,  # 设置字体                24.                 background_color=None, mode="RGBA",  # 背景颜色  25.                 max_words=500,  # 词云显示的最大词数  26.                 mask=mask,  # 设置背景图片  27.                 max_font_size=130 ,  28.                 random_state=40,  29.                 font_step= 1,  30.                 min_font_size=16,  31.                 collocations=False,  32.                 color_func = random_color_func)   33.  # 生成词云  34.  wc.generate(text)  35.  wc.to_file("temp.png")  36.  print (wc.words_)  37.  print(wc.layout_)  38.    39.  plt.figure()  40.  plt.imshow(wc, interpolation='bilinear')  41.  plt.axis("off")  42.  plt.show()