爬取新闻列表

Posted 2020-10-10 12-张振勋

• 获取单条新闻的#标题#链接#时间#来源#内容 #点击次数，并包装成一个函数。

  import requests
  from bs4 import BeautifulSoup
  import re
  
  url_main="http://news.gzcc.cn/html/xiaoyuanxinwen/"
  res = requests.get(url_main)
  res.encoding = \'utf-8\'
  
  soup = BeautifulSoup(res.text,\'html.parser\')
  li = soup.select(\'li\')
  
  def gethits(url_1):
      li_id =re.search(\'_.*/(.*).html\',url_1).groups(0)[0]
      hits = requests.get(\'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80\'.format(li_id)).text.split(\'.\')[-1].rstrip(\'\'\'\');\'\'\').lstrip(\'\'\'\'html(\'\'\')
      return hits
  
  def getpageinfo(label):
      for title_list in label:
          if len(title_list.select(\'.news-list-title\'))>0:
              href = title_list.select(\'a\')[0][\'href\']
              title = title_list.select(\'.news-list-title\')[0].text
              time = title_list.select(\'span\')[0].text
              info = title_list.select(\'span\')[1].text
  
              res_list = requests.get(href)
              res_list.encoding = \'utf-8\'
              soup_list = BeautifulSoup(res_list.text,\'html.parser\')
              text_list = soup_list.select(\'.show-content\')[0].text
  
              hits_list = gethits(href)
  
              print(\'时间：\',time,\'\\n标题：\',title,\'\\n链接：\',href,\'\\n来源：\',info,\'\\n点击次数：\',hits_list,\'\\n\')
              print(\'正文：\',text_list)
              break
  
  getpageinfo(li)

   

• 获取一个新闻列表页的所有新闻的上述详情，并包装成一个函数。

import requests
from bs4 import BeautifulSoup
import re

url_main="http://news.gzcc.cn/html/xiaoyuanxinwen/"
res = requests.get(url_main)
res.encoding = \'utf-8\'

soup = BeautifulSoup(res.text,\'html.parser\')
li = soup.select(\'li\')

def gethits(url_1):
    li_id =re.search(\'_.*/(.*).html\',url_1).groups(0)[0]
    hits = requests.get(\'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80\'.format(li_id)).text.split(\'.\')[-1].rstrip(\'\'\'\');\'\'\').lstrip(\'\'\'\'html(\'\'\')
    return hits

def getpageinfo(label):
    for title_list in label:
        if len(title_list.select(\'.news-list-title\'))>0:
            href = title_list.select(\'a\')[0][\'href\']
            title = title_list.select(\'.news-list-title\')[0].text
            time = title_list.select(\'span\')[0].text
            info = title_list.select(\'span\')[1].text

            res_list = requests.get(href)
            res_list.encoding = \'utf-8\'
            soup_list = BeautifulSoup(res_list.text,\'html.parser\')
            text_list = soup_list.select(\'.show-content\')[0].text

            hits_list = gethits(href)

            print(\'时间：\',time,\'\\n标题：\',title,\'\\n链接：\',href,\'\\n来源：\',info,\'\\n点击次数：\',hits_list,\'\\n\')
            print(\'正文：\',text_list)
            
getpageinfo(li)

 

 

• 获取所有新闻列表页的网址，调用上述函数

import requests
from bs4 import BeautifulSoup
import re

url_main="http://news.gzcc.cn/html/xiaoyuanxinwen/"
res = requests.get(url_main)
res.encoding = \'utf-8\'

soup = BeautifulSoup(res.text,\'html.parser\')
li = soup.select(\'li\')

def gethits(url_1):
    li_id =re.search(\'_.*/(.*).html\',url_1).groups(0)[0]
    hits = requests.get(\'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80\'.format(li_id)).text.split(\'.\')[-1].rstrip(\'\'\'\');\'\'\').lstrip(\'\'\'\'html(\'\'\')
    return hits

def getpageinfo(label):
    for title_list in label:
        if len(title_list.select(\'.news-list-title\'))>0:
            href = title_list.select(\'a\')[0][\'href\']
            title = title_list.select(\'.news-list-title\')[0].text
            time = title_list.select(\'span\')[0].text
            info = title_list.select(\'span\')[1].text

            res_list = requests.get(href)
            res_list.encoding = \'utf-8\'
            soup_list = BeautifulSoup(res_list.text,\'html.parser\')
            text_list = soup_list.select(\'.show-content\')[0].text

            hits_list = gethits(href)


getpageinfo(li)

pages = int(soup.select(\'.a1\')[0].text.rstrip(\'条\'))//10+1

for i in range(2,pages+1):
    url_page = "http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i)
    
    res_page = requests.get(url_page)
    res_page.encoding = \'utf-8\'

    soup_page = BeautifulSoup(res_page.text,\'html.parser\')
    list_page = soup.select(\'li\')

    getpageinfo(list_page)
    print(url_page)

• 完成所有校园新闻的爬取工作。

import requests
from bs4 import BeautifulSoup
import re

url_main="http://news.gzcc.cn/html/xiaoyuanxinwen/"
res = requests.get(url_main)
res.encoding = \'utf-8\'

soup = BeautifulSoup(res.text,\'html.parser\')
li = soup.select(\'li\')

def gethits(url_1):
    li_id =re.search(\'_.*/(.*).html\',url_1).groups(0)[0]
    hits = requests.get(\'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80\'.format(li_id)).text.split(\'.\')[-1].rstrip(\'\'\'\');\'\'\').lstrip(\'\'\'\'html(\'\'\')
    return hits

def getpageinfo(label):
    for title_list in label:
        if len(title_list.select(\'.news-list-title\'))>0:
            href = title_list.select(\'a\')[0][\'href\']
            title = title_list.select(\'.news-list-title\')[0].text
            time = title_list.select(\'span\')[0].text
            info = title_list.select(\'span\')[1].text

            res_list = requests.get(href)
            res_list.encoding = \'utf-8\'
            soup_list = BeautifulSoup(res_list.text,\'html.parser\')
            text_list = soup_list.select(\'.show-content\')[0].text

            hits_list = gethits(href)

            print(\'时间：\',time,\'\\n标题：\',title,\'\\n链接：\',href,\'\\n来源：\',info,\'\\n点击次数：\',hits_list,\'\\n\')
            print(\'正文：\',text_list)
            #break

getpageinfo(li)

pages = int(soup.select(\'.a1\')[0].text.rstrip(\'条\'))//10+1

for i in range(2,pages+1):
    url_page = "http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i)
    
    res_page = requests.get(url_page)
    res_page.encoding = \'utf-8\'

    soup_page = BeautifulSoup(res_page.text,\'html.parser\')
    list_page = soup.select(\'li\')

    getpageinfo(list_page)
    #break