每日总结6.12

今天爬取到了论文数据

python代码：

import requests
import pymysql
from bs4 import BeautifulSoup

# 链接到本地数据库
from jieba.analyse import extract_tags

db = pymysql.connect(host='127.0.0.1', port=3306, user='root', password='123456', database='z1', charset='utf8')

cursor = db.cursor()

# 定义头文件
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 "
                  "Safari/537.36 "
}
# get方法抓取数据
# url="http://openaccess.thecvf.com/CVPR2019.py"
url = "https://openaccess.thecvf.com/CVPR2019?day=2019-06-18"
html = requests.get(url)
# 使用 Beautiful Soup 解析网页
soup = BeautifulSoup(html.content, 'html.parser')

pdfs = soup.findAll("a", text="pdf")
print(len(pdfs))

lis = []
jianjie = ""
for i, pdf in enumerate(pdfs):
    pdf_name = pdf["href"].split('/')[-1]
    name = pdf_name.split('.')[0].replace("_CVPR_2019_paper", "")
    link = "https://openaccess.thecvf.com/content_CVPR_2019/html/" + name + "_CVPR_2019_paper.html"
    url1 = link
    print(url1)
    print(i)
    html1 = requests.get(url1)
    if html1:
        soup1 = BeautifulSoup(html1.content, 'html.parser')
        weizhi = soup1.find('div', attrs={'id': 'abstract'})
        if weizhi:
            jianjie = weizhi.get_text()
        authors = soup1.find_all(id="authors")
        # 论文编号
        a = authors[0].contents[3]
        a_split = a.split('.')  # 以点分割为数组
        code = a_split[1].strip()  # 去掉空格前后
        # 作者
        author = soup1.find("i")
        myauthor = author.string
        keywordlist = []
        for keyword, weight in extract_tags(jianjie.strip(), topK=5, withWeight=True):
            keywordlist.append(keyword)
        keywordliststr = ','.join(keywordlist)
        info = {
            'title': name,
            'author': myauthor,
            'abstract': jianjie,
            'link': link,
            'code': code,
            'keywords': keywordliststr}
        print(info.values())
        lis.append(info)
print(lis)

cursor = db.cursor()
for i in range(len(lis)):
    cols = ", ".join('`{}`'.format(k) for k in lis[i].keys())
    print(cols)  # '`name`, `age`'

    val_cols = ', '.join('%({})s'.format(k) for k in lis[i].keys())
    print(val_cols)  # '%(name)s, %(age)s'

    sql = "insert into lunwen(%s) values(%s)"
    res_sql = sql % (cols, val_cols)
    print(res_sql)

    cursor.execute(res_sql, lis[i])  # 将字典a传入
    db.commit()
    print("ok")