爬虫中numpy pandas的简单应用

爬取API数据

基础知识
利用requests库读取api中的信息

import requests
response = requests.get("https://api.github.com/users/qiwsir")    # ①
response
response.json()#以json格式输出数据
## 数据命名利用DataFrame进行整合
import pandas as pd
data = response.json()    # ②
login = data['login']     # ③
name = data['name']
blog = data['blog']
public_repos = data['public_repos']
followers = data['followers']
html_url = data['html_url']
df = pd.DataFrame([[login, name, blog, public_repos, followers, html_url]], 
                  columns=['login', 'name', 'blog', 'public_repos', 'followers', 'html_url'])    # ④
df

一个简单的项目案例

```python
import pandas as pd
data = response.json()    # ②
login = data['login']     # ③
name = data['name']
blog = data['blog']
public_repos = data['public_repos']
followers = data['followers']
html_url = data['html_url']
df = pd.DataFrame([[login, name, blog, public_repos, followers, html_url]], 
                  columns=['login', 'name', 'blog', 'public_repos', 'followers', 'html_url'])    # ④
df
url = "https://news.baidu.com/widget?id=LocalNews&ajax=json"
r = requests.get(url)
local_news = r.json()
local_news
news = local_news['data']['LocalNews']['data']['rows']['first']
news