|
按照网络的教程 写的 源码如下:
# -*- coding: utf-8 -*-
from urllib import urlopen
from bs4 import BeautifulSoup
import re
import pymysql.cursors
url="https://en.wikipedia.org/wiki/Main_Page"
resp=urlopen(url).read().decode('utf-8')
soup = BeautifulSoup(resp,"html.parser")
listurls = soup.find_all("a", href=re.compile("^/wiki/"))
for url in listurls:
if not re.search("\.(jpg|JPG)$",url["href"]):
print url.get_text(), " ", "https://en.wikipedia.org"+url["href"]
connection =pymysql.connect(
host='127.0.0.1',
port=3306,
user='user',
passwd='123456',
#db='vvv',
charset='utf8'
)
try:
with connection.cursor() as cursor:
sql = "insert into `urls`(`title`,`link`) values(%s,%s)"
cursor.execute(sql,(url.get_text(),"https://en.wikipedia.org"+url["href"]))
connection.commit()
finally:
#cursor.close()
connection.close()
严格按照视频教程操作的
代码 能运行
运行一次 只能 写入一条数据 到数据库 而且还只是 最后 一条
非常感谢解答!!!!!!!
|
-
数据库
|