腳本實現：獲取51cto網站某大牛文章的url，並存儲到數據庫中。
#!/usr/bin/env python
#coding:utf-8
from bs4 import BeautifulSoup
import urllib
import re
import MySQLdb
k_art_name = []
v_art_url = []
db = MySQLdb.connect('192.168.115.5','blog','blog','blog')
cursor = db.cursor()
for page in range(1,5):
page = str(page)
url = 'http://yujianglei.blog.51cto.com/all/7215578/page/' + page
request = urllib.urlopen(url)
response = request.read()
response = unicode(response,'GBK').encode('UTF-8')
soup = BeautifulSoup(response,'html.parser')
a_tag = soup.find_all(href=re.compile("^/\d{7,}/\d{7,}$"))
for i in a_tag:
art_name = i.string
art_url = 'http://yujianglei.blog.51cto.com' + i['href']
k_art_name.append(art_name)
v_art_url.append(art_url)
if len(k_art_name) == len(v_art_url):
number1 = len(k_art_name)
number2 = len(v_art_url)
for j in range(number1):
a = k_art_name[j]
b = v_art_url[j]
print a,b
sql = '''INSERT INTO blog_51cto (art_name,art_url) VALUES ("%s","%s")''' %(a,b)
try:
cursor.execute(sql)
db.commit()
except Exception, e:
print e
db.rollback()
else:
print 'k_art_name:', len(k_art_name)
print 'v_art_url:' , len(v_art_url)
cursor.close()
db.close()
# insert into blog_51cto (art_name,art_url) VALUES ("oracle 手動歸檔、自動歸檔、歸檔位置、歸檔進程","http://yujianglei.blog.51cto.com/7215578/1560485")
#CREATE DATABASE blog;
#CREATE TABLE `blog_51cto` (
# `id` int(11) NOT NULL AUTO_INCREMENT,
# `art_name` varchar(500) DEFAULT NULL,
# `art_url` varchar(500) DEFAULT NULL,
# PRIMARY KEY (`id`)
# ) ENGINE=InnoDB AUTO_INCREMENT=1609 DEFAULT CHARSET=utf8;