微博热词搜索并生成云词html（完整）_微博关键词云入口-CSDN博客

本文链接：https://blog.csdn.net/baidu_39384178/article/details/113113539
from urllib.parse import urlencode
import requests
from pyquery import PyQuery as pq
import time
import os
import csv
import json
import pandas as pd
#-----------------------------------判断是否存在文件，否则增加
if os.path.exists('微博热词.csv'):
    os.remove('微博热词.csv')
if os.path.exists('微博热词.txt'):
    os.remove('微博热词.txt')
try:
  f =open("停用词库.txt",'r')
  f.close()
except IOError:
  f = open("停用词库.txt",'w')
  f.close()

try:
  f =open("分词词典.txt",'r',encoding='utf-8')
  f.close()
except IOError:
  f = open("分词词典.txt",'w',encoding='utf-8')
  f.close()

#-----------------------------------判断是否存在文件，否则增加


base_url = 'https://m.weibo.cn/api/container/getIndex?'

headers = {
    'Host': 'm.weibo.cn',
    'Referer': 'https://m.weibo.cn/u/2830678474',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
    'X-Requested-With': 'XMLHttpRequest',
}
class SaveCSV(object):

    def save(self, keyword_list,path, item):
        """
        保存csv方法
        :param keyword_list: 保存文件的字段或者说是表头
        :param path: 保存文件路径和名字
        :param item: 要保存的字典对象
        :return:
        """
        try:
            # 第一次打开文件时，第一行写入表头
            if not os.path.exists(path):
                with open(path, "w", newline='', encoding='utf-8') as csvfile:  # newline='' 去除空白行
                    writer = csv.DictWriter(csvfile, fieldnames=keyword_list)  # 写字典的方法
                    writer.writeheader()  # 写表头的方法

            # 接下来追加写入内容
            with open(path, "a", newline='', encoding='utf-8') as csvfile:  # newline='' 一定要写，否则写入数据有空白行
                writer = csv.DictWriter(csvfile, fieldnames=keyword_list)
                writer.writerow(item)  # 按行写入数据
                print("^_^ write success")

        except Exception as e:
            print("write error==>", e)
            # 记录错误数据
            with open("error.txt", "w") as f:
                f.write(json.dumps(item) + ",\n")
            pass

def get_page(page,title): #得到页面的请求，params是我们要根据网页填的，就是下图中的Query String里的参数
    params = {
        'containerid': '100103type=1&q='+title,
        'page': page,#page是就是当前处于第几页，是我们要实现翻页必须修改的内容。
        'type':'all',
        'queryVal':title,
        'featurecode':'20000320',
        'luicode':'10000011',
        'lfid':'106003type=1',
        'title':title
    }
    url = base_url + urlencode(params)
    print(url)
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            print(page)
            return response.json()
    except requests.ConnectionError as e:
        print('Error', e.args)

# 解析接口返回的json字符串
def parse_page(json , label):
    res = []
    if json:
        items = json.get('data').get('cards')
        for i in items:
            if i == None:
                continue
            item = i.get('mblog')
            if item == None:
                continue
            weibo = {}
            weibo['id'] = item.get('id')
            weibo['label'] = label
            weibo['text'] = pq(item.get('text')).text().replace(" ", "").replace("\n" , "")
            res.append(weibo)
    return res

if __name__ == '__main__':

    title = input("请输入搜索关键词：")
    path = "微博热词.csv"
    item_list = ['id','text', 'label']
    s = SaveCSV()
    for page in range(10,20):#循环页面
        try:
            time.sleep(1)         #设置睡眠时间，防止被封号
            json = get_page(page , title )
            results = parse_page(json , title)
            if requests == None:
                continue
            for result in results:
                if result == None:
                    continue
                print(result)


                s.save(item_list, path , result)
        except TypeError:
            print("完成")
            continue

#数据转txt------------------------------------
data = pd.read_csv('微博热词.csv', encoding='utf-8')
with open('微博热词.txt','a+', encoding='utf-8') as f:
    for line in data.values:
        f.write((str(line[0])+'\t'+str(line[1])+'\n'))


#---------------------------------词云图
#!/usr/bin/env python3
# -*- coding:utf-8 -*-
# Author LQ6H

import jieba
from collections import Counter
import pyecharts.options as opts
from pyecharts.charts import WordCloud


def get_text():

    # f=open("text1.txt",encoding="gbk")
    f = open("微博热词.txt", encoding="utf-8")
    lines=f.read()

    text=lines.split("\n\n")

    return "".join(text)




def split_word(text):

    jieba.load_userdict("分词词典.txt")
    # word_list=list(jieba.cut_for_search(text))#精准模式后搜素模式
    word_list = list(jieba.cut(text))#默认进准模式



    with open("停用词库.txt") as f:
        meaningless_word=f.read().splitlines()

    result=[]

    for i in word_list:

        if i not in meaningless_word:
            result.append(i.replace(" ",""))

    return result

def word_counter(words):

    words_counter=Counter(words)

    words_list=words_counter.most_common(101)#排名前N
    fc = words_list
    with open('分词排名.txt', 'a+', encoding='utf-8') as f:
        for line in fc:
            f.write((str(line[0]) + '\t' + str(line[1]) + '\n'))
    return words_list


def word_cloud(data):
    (
        WordCloud()
            .add(
            series_name="热词分析",
            data_pair=data,
            word_gap=5,
            word_size_range=[20,100],#词的大小[20,500]
            shape="",
            rotate_step=90,

            # width=2000,
            # height=1000
            # mask_image="书.jpg"
        ).set_global_opts(
            title_opts=opts.TitleOpts(
                title="热词分析",title_textstyle_opts=opts.TextStyleOpts(font_size=23)
            ),
            tooltip_opts=opts.TooltipOpts(is_show=True),
        )
        .render("微博热词.html")
    )


def main():

    text=get_text()

    words=split_word(text)

    data=word_counter(words)

    word_cloud(data)

if __name__ == '__main__':

    main()