python 爬取頁面數據，生成詞雲和網絡圖

 

簡單的爬取頁面數據，並生成詞雲和網絡圖

需要安卓  networkx wordcloud 包

代碼如下

 

# @Author  :whyCai
# @Time    :2020/10/17 10:35
from time import sleep

import requests,json,jieba,wordcloud,networkx as nx,jieba.posseg as jp
from matplotlib import pyplot as plt

"""
#爬取頁面的數據
def getCommText():
    '''
    爬取頁面的數據
    :return: 
    '''
    text = ''
    url = 'https://xxxxxxx'
    headers = {'content-type': 'application/json'}

    for i in range(0,300):
        data = {"pageIndex": i+1,"xxxx":1}
        r = requests.post(url, data=json.dumps(data), headers=headers)
        res = json.loads(r.text)
        #獲取接口的字段值
        resContent = res['result']['items']
        lenComm = len(resContent)
        # 獲取接口的字段值
        for j in range(0,lenComm):
            # text = text + resContent[j]['content']+' '
            print(resContent[j]['content'])
        sleep(0.2)
    # print(text)
    # return text
getCommText()
"""

"""
#生成詞雲

#讀取數據
f = open('xxx.txt',encoding='utf-8')
text = f.read()
txtlist = jieba.lcut(text)
txtlist = " ".join(txtlist)
w = wordcloud.WordCloud(width=1000,height=700,background_color='white',font_path='msyh.ttc')
w.generate(txtlist)
#生成詞雲
w.to_file('output2-poem.png')
"""


"""
#生成網絡圖

#text 為 上面詞雲中的 text = f.read()
words = jp.lcut(text)
G = nx.MultiDiGraph()  
# 添加節點
for word in words:
    G.add_node(word.flag)
# 添加邊
for i in range(len(words) - 1):
    G.add_edge(words[i].flag, words[i+1].flag)
# 繪圖
nx.draw(G, alpha=0.8, with_labels=True, node_color='lightgreen', font_size=36, node_size=999, width=2)
# 展示
plt.show()
"""

 

 

參考博客：

詞雲：https://www.cnblogs.com/wkfvawl/p/11585986.html

網絡圖：https://blog.csdn.net/your_answer/article/details/79189660