作业来源:https://edu.cnblogs.com/campus/gzcc/GZCC-16SE1/homework/3002
0.从新闻url获取点击次数,并整理成函数
- newsUrl
- newsId(re.search())
- clickUrl(str.format())
- requests.get(clickUrl)
- re.search()/.split()
- str.lstrip(),str.rstrip()
- int
- 整理成函数
- 获取新闻发布时间及类型转换也整理成函数
1.从新闻url获取新闻详情: 字典,anews
代码如下:
#获取一条新闻的详情
import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
def click(url):
id = re.findall('(\d{1,5})',url)[-1]#返回所有匹配的字符串的字符串列表的最后一个
clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(id)
resClick = requests.get(clickUrl)
newsClick = int(resClick.text.split('.html')[-1].lstrip("('").rstrip("');"))
return newsClick
#时间
def newsdt(showinfo):
newsDate = showinfo.split()[0].split(':')[1]
newsTime = showinfo.split()[1]
newsDT = newsDate+' '+newsTime
dt = datetime.strptime(newsDT,'%Y-%m-%d %H:%M:%S')#转换成datetime类型
return dt
#内容
def anews(url):
newsDetail = {}
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')
newsDetail['newsTitle'] = soup.select('.show-title')[0].text#题目
showinfo = soup.select('.show-info')[0].text
newsDetail['newsDT'] = newsdt(showinfo)#时间
newsDetail['newsClick'] = click(newsUrl)#点击次数
return newsDetail
newsUrl = 'http://news.gzcc.cn/html/2019/xiaoyuanxinwen_0404/11155.html'
print(anews(newsUrl))
运行结果:
2.从列表页的url获取新闻url:列表append(字典) alist
代码如下:
def alist(url):
res = requests.get(listUrl)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text, 'html.parser')
newsList = []
for news in soup.select('li'):#获取li元素
if len(news.select('.news-list-title'))>0:#如果存在新闻题目
newsUrl = news.select('a')[0]['href']#获取新闻的链接
newsDesc = news.select('.news-list-description')[0].text#获取摘要文本
newsDict = anews(newsUrl)#通过链接获取题目时间点击数
newsDict['description'] = newsDesc
newsList.append(newsDict)#把每个新闻的信息放进字典扩展到列表里
return newsList
listUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
print(alist(listUrl))
运行结果:
3.生成所页列表页的url并获取全部新闻 :列表extend(列表) allnews
代码如下:
allnews = []
for i in range(50,60):
listUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
allnews.extend(alist(listUrl))
print(len(allnews))
print(allnews)
运行结果:
*每个同学爬学号尾数开始的10个列表页
4.设置合理的爬取间隔
import time
import random
time.sleep(random.random()*3)
代码如下:
for i in range(5):
print(i)
time.sleep(random.random() * 3) # 设置爬取的时间间隔
print(newsdf)
5.用pandas做简单的数据处理并保存
保存到csv或excel文件
newsdf.to_csv(r'F:\duym\爬虫\gzccnews.csv')
保存到数据库
import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
newsdf.to_sql('gzccnewsdb',db)
代码如下:
import pandas as pd
import time
import random
import sqlite3
pd.Series(allnews)#保存文件
newsdf = pd.DataFrame(allnews)
for i in range(5):
print(i)
time.sleep(random.random() * 3) # 设置爬取的时间间隔
print(newsdf)
newsdf.to_csv(r'D:\Download\gzcc.csv', encoding='utf_8_sig') # 保存成csv格式,为避免乱码,设置编码格式为utf_8_sig
with sqlite3.connect(r'D:\Download\gzccnewsdb2.sqlite') as db: # 保存文件为sql
newsdf.to_sql('gzccnewsdb2', db)
运行结果: