Python爬取新型冠状病毒“谣言”新闻进行数据分析

import requests
import pandas as pd
class SpiderRumor(object):
 def __init__(self):
 self.url = "https://vp.fact.qq.com/loadmore?artnum=0&page=%s"
 self.header = {
  "User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1",
 }
 def spider_run(self):
 df_all = list()
 for url in [self.url % i for i in range(30)]:
  data_list = requests.get(url, headers=self.header).json()["content"]
  temp_data = [[df["title"], df["date"], df["result"], df["explain"], df["tag"]] for df in data_list]
  df_all.extend(temp_data)
  print(temp_data[0])
 pd.DataFrame(df_all, columns=["title", "date", "result", "explain", "tag"]).to_csv("冠状病毒谣言数据.csv", encoding="utf_8_sig")
if __name__ == '__main__':
 spider = SpiderRumor()
 spider.spider_run()

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
# Windows系统设置中文字体
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus'] = False
data = pd.read_csv("/冠状病毒谣言数据.csv"")
labels = data["explain"].value_counts().index.tolist()
sizes = data["explain"].value_counts().values.tolist()
colors = ['lightgreen', 'gold', 'lightskyblue', 'lightcoral']
plt.figure(figsize=(15,8))
plt.pie(sizes, labels=labels,
 colors=colors, autopct='%1.1f%%', shadow=True, startangle=50) # shadow=True 表示阴影
plt.axis('equal') # 使图居中
plt.show()

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
# Windows系统设置中文字体
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus'] = False

data = pd.read_csv("/冠状病毒谣言数据.csv"")
df = pd.Series([j for i in [eval(i) for i in data["tag"].tolist()] for j in i]).value_counts()[:20]
X = df.index.tolist()
y = df.values.tolist()
plt.figure(figsize=(15, 8)) # 设置画布
plt.bar(X, y, color="orange")
plt.tight_layout()
# plt.grid(axis="y")
plt.grid(ls='-.')
plt.show()