Python数据可视化 之 使用API

使用requests模块来请求网站数据

import requests


#执行API调用并存储响应
url = 'https://api.github.com/search/repositories?q=language:python&sort=stars'
r = requests.get(url)
print("Statuscode:", r.status_code)

#将API响应存储在一个变量中
response_dict = r.json()
print("Repositories returned:", response_dict['total_count'])#包含仓库总数

#探索有关仓库的信息
repo_dicts = response_dict['items']
print("Repositories returned:", len(repo_dicts))

#研究第一个仓库
repo_dict = repo_dicts[0]
print("\nKeys:", len(repo_dict))
for key in sorted(repo_dict.keys()):
    print(key)

print("\nSelected information about first repository:")
print('Name:', repo_dict['name'])
print('Owner:', repo_dict['owner']['login'])
print('Stars:', repo_dict['stargazers_count'])
print('Repository:', repo_dict['html_url'])
print('Created:',repo_dict['created_at'])
print('Updated:', repo_dict['updated_at'])
print('Description:', repo_dict['description'])

Output:

-------snip--------
Selected information about first repository:
Name: awesome-python
Owner: vinta
Stars: 66036
Repository: https://github.com/vinta/awesome-python
Created: 2014-06-27T21:00:06Z
Updated: 2019-04-19T12:49:58Z
Description: A curated list of awesome Python frameworks, libraries, software and resources

使用Pygal可视化仓库：

添加一个参数配置来定义图表参数，自定义图表中每个条形的描述信息以及可单击的链接

mport requests
import pygal
from pygal.style import LightColorizedStyle as LCS, LightenStyle as LS


#执行API调用并存储响应
url = 'https://api.github.com/search/repositories?q=language:python&sort=stars'
r = requests.get(url)
print("Statuscode:", r.status_code)

#将API响应存储在一个变量中
response_dict = r.json()
print("Repositories returned:", response_dict['total_count'])#包含仓库总数

#探索有关仓库的信息
repo_dicts = response_dict['items']

names, plot_dicts = [], []
for repo_dict in repo_dicts:
    names.append(repo_dict['name'])
    plot_dict ={
        'value': repo_dict['stargazers_count'],
        'label': str(repo_dict['description']),
        'xlink': repo_dict['html_url']
    }
    plot_dicts.append(plot_dict)
#可视化
my_style = LS('#333366', base_style=LCS)

my_config = pygal.Config()#创建配置实例
my_config.x_label_rotation = 45#X轴标签顺时针旋转45度
my_config.show_legend = False#隐藏图例
my_config.title_font_size = 24#图表标题字体大小
my_config.label_font_size = 14#副标签
my_config.major_label_font_size = 18#主标签，Y轴上为5000整数倍的刻度，不是很明白这个是怎么回事
my_config.truncate_label = 15#将较长的项目名缩短为15个字符
my_config.show_y_guides = False#隐藏图表中的水平线
my_config.width = 1000#自定义表宽

chart = pygal.Bar(my_config, style=my_style)
chart.title = 'Most-Starred Python Projects on GitHub'
chart.x_labels = names

chart.add('', plot_dicts)
chart.render_to_file('python_repos.svg')

Figure:

使用Hacker News API:

通过一个API调用获取其上当前热门文章的ID，再查看前30篇文章,打印其标题、到讨论页面的链接以及文章现有的评论数。（这里运行报错应该是爬虫的问题，小白表示

目前不知道咋整，只附代码。）

import requests
from operator import itemgetter


url = 'https://hacker-news.firebaseio.com/v0/topstories.json'
r = requests.get(url)
print("Status code:", r.status_code)

submission_ids = r.json()
submission_dicts = []
for submission_id in submission_ids[:30]:
    url = ('http://hacker-news.firebase.com/v0/item/' +
           str(submission_id) + '.json')
    submission_r = requests.get(url)
    print(submission_r.status_code)
    response_dict = submission_r.json()

    submission_dict = {
        'title': response_dict['title'],
        'link': 'http://news.ycombinator.com/item?id=' + str(submission_id),
        'comments': response_dict.get('descendants', 0)
    }
    submission_dicts.append(submission_dict)

submission_dicts = sorted(submission_dicts, key=itemgetter('comments'),
                          reverse=True)
for submission_dict in submission_dicts:
    print("\nTitle:", submission_dict['title'])
    print("Discussion link:", submission_dict['link'])
    print("Comments:", submission_dict['comments'])