Python 爬取知乎用户属性生成词语

Posted 2020-10-20 软测小生

 

代码如下：

# -*- coding:utf-8 -*-

import requests
import pandas as pd
import time

import matplotlib.pyplot as plt
from wordcloud import WordCloud
import jieba

header={
    \'authorization\':\'Bearer 2|1:0|10:1515395885|4:z_c0|92:Mi4xOFQ0UEF3QUFBQUFBRU1LMElhcTVDeVlBQUFCZ0FsVk5MV2xBV3dDLVZPdEhYeGxaclFVeERfMjZvd3lOXzYzd1FB|39008996817966440159b3a15b5f921f7a22b5125eb5a88b37f58f3f459ff7f8\',
    \'User-Agent\':\'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.94 Safari/537.36\',
    \'X-UDID\':\'ABDCtCGquQuPTtEPSOg35iwD-FA20zJg2ps=\',
}

user_data = []
def get_user_data(page):
    for i in range(page):
        url = \'https://www.zhihu.com/api/v4/members/excited-vczh/followees?include=data%5B*%5D.answer_count%2Carticles_count%2Cgender%2Cfollower_count%2Cis_followed%2Cis_following%2Cbadge%5B%3F(type%3Dbest_answerer)%5D.topics&offset={}&limit=20\'.format(i*20)
#response = requests.get(url, headers=header).text
        response = requests.get(url, headers=header).json()[\'data\']#[\'data\']   只有JSON格式中选择data节点
        user_data.extend(response)
        print(\'正在爬取%s页\' % str(i+1))
        time.sleep(1)

if __name__==\'__main__\':
    get_user_data(10)
    #pandas 的函数 from_dict()可以直接将一个response变成一个对象
    #df = pd.DataFrame.from_dict(user_data)
    #df.to_csv(\'D:/PythonWorkSpace/TestData/zhihu/user2.csv\')
    df = pd.DataFrame.from_dict(user_data).get(\'headline\')
    df.to_csv(\'D:/PythonWorkSpace/TestData/zhihu/headline.txt\')

    text_from_file_with_apath = open(\'D:/PythonWorkSpace/TestData/zhihu/headline.txt\').read()
    wordlist_after_jieba = jieba.cut(text_from_file_with_apath, cut_all=True)
    wl_space_split = " ".join(wordlist_after_jieba)

    my_wordcloud = WordCloud().generate(wl_space_split)

    plt.imshow(my_wordcloud)
    plt.axis("off")
    plt.show()

需要安装准备的库：

pip install matplotlib
pip install jieba
pip install wordcloud(发现这方法安装不成功)

换种安装方式到 https://github.com/amueller/word_cloud 这里下载库文件，解压，然后进入到解压后的文件，按住shift+鼠标右键 打开命令窗口运行一下命令：

python setup.py install

 然后同样报错


 然后我又换了一张安装方式：
到 http://www.lfd.uci.edu/~gohlke/pythonlibs/#wordcloud 页面下载所需的wordcloud模块的whl文件，下载后进入存储该文件的路径，按照方法一，执行“pip install wordcloud-1.3.3-cp36-cp36m-win_amd64.whl”，这样就会安装成功。


 

然后生成词云的代码如下：

text_from_file_with_apath = open(\'D:\\Python\\zhihu\\headline.txt\',\'r\',encoding=\'utf-8\').read()
wordlist_after_jieba = jieba.cut(text_from_file_with_apath, cut_all=True)
wl_space_split = " ".join(wordlist_after_jieba)

my_wordcloud = WordCloud().generate(wl_space_split)

plt.imshow(my_wordcloud)
plt.axis("off")
plt.show()

但是发现不显示中文，这可就头疼了。
显示的是一些大大小小的彩色框框。这是因为，我们使用的wordcloud.py中，FONT_PATH的默认设置不识别中文。
仔细研究之后做了改进，终于可以正常显示中文了

text_from_file_with_apath = open(\'D:\\Python\\zhihu\\headline.txt\',\'r\',encoding=\'utf-8\').read()
wordlist_after_jieba = jieba.cut(text_from_file_with_apath, cut_all=True)
wl_space_split = " ".join(wordlist_after_jieba)
#FONT_PATH = os.environ.get("FONT_PATH", os.path.join(os.path.dirname(__file__), "simkai.ttf"))
cloud = WordCloud(
    #设置字体，不指定就会出现乱码
    font_path="simkai.ttf",
    #设置背景色
    background_color=\'white\',
    #允许最大词汇
    max_words=9000,
    #词云形状
    #mask=color_mask
    )#.generate(wl_space_split)
## 产生词云
word_cloud = cloud.generate(wl_space_split)
word_cloud.to_file(\'D:\\Python\\zhihu\\headline.jpg\')#将图片保存到指定文件中
#直接显示图片，并且可编辑
# plt.imshow(word_cloud)
# plt.axis("off")
# plt.show()

　　 

 

坑：

Python读取文件时经常会遇到这样的错误：python3.4 UnicodeDecodeError: \'gbk\' codec can\'t decode byte 0xff in position 0: illegal multibyte sequence

import codecs,sys
 f = codecs.open("***.txt","r","utf-8")
指明打开文件的编码方式就可以消除错误了