#!/usr/lib/python3.6
#encoding = utf-8
#爬取一个博客的基本信息
#本爬虫仅用于学习，纯属爱好，虽然本爬虫很简单，但还是请大家不要滥用

import requests
from bs4 import BeautifulSoup

# 请求头
headers = {
	'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:59.0) Gecko/20100101 Firefox/59.0'
} 

#博客网址
url = ""

#爬取博客基本信息的函数
def getOneBlogDetails(url):

    #获取网页的数据
	r = requests.get(url, headers=headers, timeout=100)
        
    #解析网页，BeautifulSoup的官方文档：https://www.crummy.com/software/BeautifulSoup/bs4/doc/index.zh.html
	soup = BeautifulSoup(r.text, "html.parser")

	Name = soup.find('a', id="uid").text
	My_url = soup.find('a', id="uid").get('href')

	info = soup.find('div', class_="data-info d-flex item-tiling")
	#info_list1: [<dt><a href="?t=1">原创</a></dt>, <dt>粉丝</dt>, <dt>喜欢</dt>, <dt>评论</dt>]
	info_list1 = info.find_all('dt')
	# info_list2: [<span class="count">77</span>, <span class="count" id="fan">0</span>, <span class="count">0</span>, <span class="count">1</span>]
	info_list2 = info.find_all('span', class_='count')


	info1 = soup.find('div', class_="grade-box clearfix")
	info1_list = info1.find_all('dl')
	Base = {}
	Base1 = {}
	for i in range(len(info_list2)):
		Base[info_list1[i].text] = info_list2[i].text
    
	for link in info1_list:
		key = link.find('dt').text 
		if link.find('dd').text.strip() == '':
			values = link.find('a').get('title')[0:2] 
		else:
			values = link.find('dd').text.strip()
		Base1[key] = values

	print( "博主姓名: " + Name )
	print( "个人主页: " + My_url)
	for key in Base.keys():
		print( key + ": " + Base[key])

	for key in Base1.keys():
		print( key  + Base1[key])

# 调用函数
getOneBlogDetails(url)