Python实现电视剧狂飙角色热度条形图

import datetime import requests import json word_url = 'http://index.baidu.com/api/SearchApi/thumbnail?area=0&word={}' def get_html(url): headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36", "Host": "index.baidu.com", "Referer": "http://index.baidu.com/v2/main/index.html", "Cipher-Text": "1652425237825_1652501356206_VBpwl9UG8Dvs2fAi91KToRTSAP7sDsQU5phHL97raPDFJdYz3fHf9hBAQrGGCs+qJoP7yb44Uvf91F7vqJLVL0tKnIWE+W3jXAI30xx340rhcwUDQZ162FPAe0a1jsCluJRmMLZtiIplubGMW/QoE/0Pw+2caH39Ok8IsudE4wGLBUdYg1/bKl4MGwLrJZ7H6wbhR0vT5X0OdCX4bMJE7vcwRCSGquRjam03pWDGZ51X15fOlO0qMZ2kqa3BmxwNlfEZ81l3L9nZdrc3/Tl4+mNpaLM7vA5WNEQhTBoDVZs6GBRcJc/FSjd6e4aFGAiCp1Y8MD66chTiykjIN51s7gbJ44JfVS0NjBnsvuF55bs=" } cookies = { 'Cookie': 你的cookie } response = requests.get(url, headers=headers, cookies=cookies) return response.text def decrypt(t, e): n = list(t) i = list(e) a = {} result = [] ln = int(len(n) / 2) start = n[ln:] end = n[:ln] for j, k in zip(start, end): a.update({k: j}) for j in e: result.append(a.get(j)) return ''.join(result) def get_ptbk(uniqid): url = 'http://index.baidu.com/Interface/ptbk?uniqid={}' resp = get_html(url.format(uniqid)) return json.loads(resp)['data'] def get_data(keyword, start='2011-01-02', end='2023-01-02'): url = "https://index.baidu.com/api/SearchApi/index?area=0&word=[[%7B%22name%22:%22{}%22,%22wordType%22:1%7D]]&startDate={}&endDate={}".format(keyword, start, end) data = get_html(url) data = json.loads(data) uniqid = data['data']['uniqid'] data = data['data']['userIndexes'][0]['all']['data'] ptbk = get_ptbk(uniqid) result = decrypt(ptbk, data) result = result.split(',') start = start_date.split("-") end = end_date.split("-") a = datetime.date(int(start[0]), int(start[1]), int(start[2])) b = datetime.date(int(end[0]), int(end[1]), int(end[2])) node = 0 for i in range(a.toordinal(), b.toordinal()): date = datetime.date.fromordinal(i) print(date, result[node]) node += 1 with open('data.csv', 'a+', encoding='gbk') as f: f.write(keyword + ',' + date.strftime('%Y-%m-%d') + ',' + result[node] + '\n') if __name__ == '__main__': names = ['唐小龙', '孟德海', '孟钰', '安欣', '安长林', '徐忠', '徐江', '曹闯', '李响', '李宏伟', '李有田', '杨健', '泰叔', '赵立冬', '过山峰', '陆寒', '陈书婷', '高启兰', '高启强', '高启盛', '高晓晨'] for keyword in names: start_date = "2023-01-14" end_date = "2023-02-04" get_data(keyword, start_date, end_date)