第一个爬虫

Posted 2020-09-27 Sip

import requests
import pandas as pd
from bs4 import BeautifulSoup
import json
import pandas


def comments(newsurl): #获取评论信息
    commentsurl = ‘http://comment5.news.sina.com.cn/page/info?version=1&format=js&channel=gn&newsid=comos-{}&group=&compress=0&ie=utf-8&oe=utf-8&page=1&page_size=20‘  
    x = newsurl.split(‘/‘)[-1].lstrip(‘doc-i‘).rstrip(‘.shtml‘)
    jd = json.loads(requests.get(commentsurl.format(x)).text.strip(‘var data=‘))
    return jd[‘result‘][‘count‘][‘total‘]

def getNewsDetail(newsurl): #获取新闻内容
    result = {}
    sample = requests.get(newsurl)
    sample.encoding = ‘utf-8‘
    soup = BeautifulSoup(sample.text,‘html.parser‘)
    result[‘title‘] = soup.select(‘.page-header‘)[0].text
    result[‘dt‘] = soup.select(‘.time-source‘)[0].contents[0].strip()
    result[‘article‘] = ‘     ‘.join([p.text.strip() for p in soup.select(‘#artibody p‘)[0:-1]])
    result[‘resouce‘] = soup.select(‘.time-source‘)[0].contents[1].text
    result[‘editor‘] = soup.select(‘.article-editor‘)[0].text.lstrip(‘责任编辑：‘)
    result[‘comments‘] = comments(newsurl)
    return result
    
def getnews(url): #获取主页面新闻连接
    url.encoding=‘utf-8‘
    alllist = []
    soup = BeautifulSoup(url.text,‘html.parser‘)
    for a in soup.select(‘.news-item‘):
        if len(a.select(‘h2‘)) > 0:
            newsurl = a.select(‘a‘)[0][‘href‘]
            alllist.append(getNewsDetail(newsurl))
            df = pandas.DataFrame(alllist)
            df.to_excel(‘news.xlsx‘,sheet_name=‘Random Data‘) #导出数据到excel中
          
            
url = requests.get(‘http://news.sina.com.cn/china/‘)
getnews(url)  #新浪国内新闻



    
----------------------------------------------------------------------------------------------------------------------------------------------
将主页面通过get方法拿到--通过BeautifulSoup进行剖析--利用开发者工具找出标题、内文、编辑、评论等信息所在位置--利用BeautifulSoup中的select方法对所需信息进行提取，并且

存入字典resul{}中--通过循环将每则新闻信息append到最后的列表alllist--使用pandas函数、DataFrame方法将列表整理，最终导出为excel表格