python爬虫采集文章基础信息保存excel案例
import requests
from bs4 import BeautifulSoup
import openpyxl
wb = openpyxl.Workbook()
sheet = wb.active
sheet.title = '文章'
sheet['A1'] = '标题'
sheet['b1'] = '摘要'
sheet['c1'] = 'url'
sheet['d1'] = '发布时间'
sheet['e1'] = 'pic地址'
#引用requests库
for i in range(10):
res = requests.get('https://www.jb51.net/html5/list551_'+ str(i) +'.html')
res.encoding='gbk'
#定义Reponse对象的编码为utf-8。
html = res.text
#把Response对象的内容以字符串的形式返回
soup = BeautifulSoup(html,'html.parser')
items = soup.find_all(class_='item-inner')
for item in items:
title = item.find('p').text
zhaiyao = item.find(class_='item-infode').text
url = 'https://www.jb51.net'+item.find('p').find('a')['href']
addtime = item.find(class_='lbtn').text
try:
picadress = item.find('img')['src']
except:
picadress = ''
print('标题',title)
print('摘要',zhaiyao)
print('url',url)
print('发布时间',addtime)
print('图片地址',picadress)
sheet.append([title,zhaiyao,url,addtime,picadress])
print('----------------')
wb.save(r'c:/Users/Administrator/Desktop/文章.xlsx')