infolite
demo
# coding: utf-8
# ## pyquery 抓取腾讯新闻
# In[7]:
import requests
from pyquery import PyQuery as pq
html = requests.get('http://news.qq.com/').text
news_items = pq(html).find('.linkto').items()
news_arr = []
for news in news_items:
news_arr.append({'title' : news.text(), 'url' : news.attr('href')})
news_arr[0]
# In[14]:
import pandas
import datetime
news_df = pandas.DataFrame(news_arr)
news_df.to_excel('{}.xlsx'.format(datetime.date.today().strftime('%Y-%m-%d')))
标签:xlsx,arr,pyquery,python,items,df,news,import From: https://blog.51cto.com/u_11290086/5808979