# -*- coding: utf-8 -*-
"""
Created on Thu Jan  7 02:44:53 2020

@author: honey

学习项目实战2，爬取本博客文章访问排名
"""

import requests
from bs4 import BeautifulSoup
import pandas as pd

#获取采集的链接
def get_url(n):
    urllist = []
    for i in range(n):
        urllist.append('https://qinzc.me/page/%i' % (i+1))
    return urllist

#采集数据
def get_data(url,head,c_dic):
    #访问链接
    ri = requests.get(url, headers=head, cookies=c_dic)

    #解析html数据
    soup = BeautifulSoup(ri.text, 'lxml')
    lis = soup.find('div',id="content").find_all('article',class_="post-list")

    #数据序列化
    data = []
    for li in lis:
        data_dict = {}
        data_dict['标题'] = li.h2.a.text
        data_dict['日期'] = li.find('span', class_="ptime").text
        data_dict['类别'] = li.find('span', class_="pcate").text.replace('\n','').replace(' ','')
        data_dict['人气'] = li.find('span', class_="pcomm").text.replace('\r','').replace('\n','').replace(' ','')
        data_dict['简介'] = li.find('div', class_="post-excerpt").text
        data.append(data_dict)
    return data

if name == "main":
    url = get_url(23)  #获取需要采集的链接, 获取分页网址

    #获取Agent,cookies
    cookie = 'commentposter=%E5%8C%BF%E5%90%8D; UM_distinctid=16e12947eda616-0d920e3bb94c44-7711439-1fa400-16e12947edba2e; CNZZDATA1260945619=120386725-1572267166-%7C1578310466'
    head = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36'}

    ##生成cookies字典表
    c_dic = {}
    cookies_tmp = cookie.split('; ')

    for n in cookies_tmp:
        c_dic[n.split('=')[0]] = n.split('=')[1]

    #开始正式采集数据
    data_lst = []
    error_lst = []

    for u in url:
        try:
            data_lst.extend(get_data(u,head,c_dic))
            print('成功采集数据 %i' % len(data_lst))
        except:
            error_lst.append(u)
            print('数据采集失败，数据网址为：',u)
    print(data_lst)        
        #获取数据信息页面网址

    datadf = pd.DataFrame(data_lst)
        # 数据清洗

    datadf.to_excel('D:/python/爬虫/qinzc.xlsx')
        # 导出excel