2021.05.20 刘一辰的软件工程随笔

今日目标：使用python爬取、存取数据：

今日总结：

from lxml import etree
from pymysql import connect
from jieba.analyse import *
import requests
class CVPR:
# 保存数据
def saveContent_list(self,title,zhaiyao,guanjian,lianjie):
# 打开数据库连接（ip/数据库用户名/登录密码/数据库名）
con = connect("localhost", "root", "a3685371", "pachong")
# 使用 cursor() 方法创建一个游标对象 cursor
cursors = con.cursor()
# 使用 execute() 方法执行 SQL 查询返回的是你影响的行数
row = cursors.execute("insert into CVPR values(%s,%s,%s,%s)", (title,zhaiyao,guanjian,lianjie))
# 使用 fetchone() 方法获取数据.
con.commit()
# 关闭数据库连接（别忘了）
con.close()
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"
}
url = "http://openaccess.thecvf.com/CVPR2019.py"
proxies = {
"http": "http://211.147.226.4",
"https": "http://122.200.90.12",
}
cvpr = CVPR()
response = requests.get(url,headers=headers)
html_str = etree.HTML(response.content.decode())
#获得标题
hrefs = html_str.xpath("//div[@id='content']/dl/dt/a/@href")
for href in hrefs:
href = "http://openaccess.thecvf.com/{0}".format(href)
response2 = requests.get(href,headers=headers)
html_str = etree.HTML(response2.content.decode())
lunwens = {}
title = html_str.xpath("//div[@id='content']/dl/dd//div[@id='papertitle']/text()")
lianjie = html_str.xpath("//div[@id='content']/dl/dd//a/@href")
zhaiyao = html_str.xpath("//div[@id='content']/dl/dd//div[@id='abstract']/text()")
for keyword, weight in extract_tags(zhaiyao[0].strip(), topK=5, withWeight=True):

try:
cvpr.saveContent_list(title,zhaiyao,keyword,lianjie)
print("存入成功")
except:
print("存入失败")