爬虫 药品库条款 不报错 入库过程丢失数据
爬取求医网的所有药品信息:http://ypk.qiuyi.cn/index.html
首先获取三个urls:
import MySQLdb
import requests
from bs4 import BeautifulSoup
from mysqldb import *
db = MySQLdb.connect("localhost", "root", "", "表名", charset='utf8', port=3306)
cursor = db.cursor()
headers={
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_3) AppleWebKit/..."
}
sql = """SELECT * FROM urls"""
datas = executesql(sql,[],'query')
for i in datas