摘要:爬取CVPR2018论文的内容:标题,简介,关键字,论文链接
1、数据库表的创建(MySQL)
注意:abstract长度不定,所以类型应为text,避免入坑
2、python爬取
import requests
from bs4 import BeautifulSoup
import pymysql
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'} # 创建头部信息
url = 'http://openaccess.thecvf.com/CVPR2018.py'
print(url)
r = requests.get(url, headers=headers)
content = r.content.decode('utf-8')
soup = BeautifulSoup(content, 'html.parser')
dts = soup.find_all('dt', class_='ptitle')
print(dts)
hts = 'http://openaccess.thecvf.com/'
# 数据爬取
alllist = []
for i in range(len(dts)):
print('这是第' + str(i) + '个')
title = dts[i].a.text.strip()
href = hts + dts[i].a['href']
r = requests.get(href, headers=headers)
content = r.content.decode('utf-8')
soup = BeautifulSoup(content, 'html.parser')
# print(title,href)
divabstract = soup.find(name='div', attrs={"id": "abstract"})
abstract = divabstract.text.strip()
# print('第'+str(i)+'个:',abstract)
alllink = soup.select('a')
link = hts + alllink[4]['href'][6:]
keyword = str(title).split(' ')
keywords = ''
for k in range(len(keyword)):
if (k == 0):
keywords += keyword[k]
else:
keywords += ',' + keyword[k]
value = (title, abstract, link, keywords)
alllist.append(value)
print(alllist)
tuplist = tuple(alllist)
# 数据保存
db = pymysql.connect("localhost", "root", "123456", "lunwen", charset='utf8')
cursor = db.cursor()
sql_cvpr = "INSERT INTO lunwens(title, abstract, link, keywords) values (%s,%s,%s,%s)"
try:
cursor.executemany(sql_cvpr, tuplist)
db.commit()
except:
print('执行失败,进入回调3')
db.rollback()
db.close()