python3.5

先安裝庫或者擴展

1 requests第三方擴展庫

pip3 install requests

2 pymysql

pip3 install pymysql

3 lxml

pip3 install lxml

4 貼個代碼

#!/usr/bin/env python
# coding=utf-8

import requests
from bs4 import BeautifulSoup
import pymysql

print(‘連接到mysql服務器...‘)
db = pymysql.connect("localhost","root","root","python
 
")
print(‘連接上了!‘)
cursor = db.cursor()
cursor.execute("DROP TABLE IF EXISTS COLOR")
sql = """CREATE TABLE COLOR (
        Color CHAR(20) NOT NULL,
        Value CHAR(10),
        Style CHAR(50) )"""

cursor.execute(sql)

hdrs = {‘User-Agent‘:‘Mozilla/5.0 (X11; Fedora; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko)
 
‘}

url = "http://html-color-codes.info/color-names/"

r = requests.get(url, headers = hdrs)
soup = BeautifulSoup(r.content.decode(‘gbk‘, ‘ignore‘), ‘lxml‘)
trs = soup.find_all(‘tr‘)   # 獲取全部tr標簽成為一個列表
for tr in trs:              # 遍歷列表裏所有的tr標簽單項
    style = tr.get(‘style‘) # 獲取每個tr標簽裏的屬性style
    tds = tr.find_all(‘
 
td‘) # 將每個tr標簽下的td標簽獲取為列表
    td = [x for x in tds]   # 獲取的列表
    name = td[1].text.strip()       # 直接從列表裏取值
    hex = td[2].text.strip()
    # print u‘顏色: ‘ + name + u‘顏色值: ‘+ hex + u‘背景色樣式: ‘ + style
    # print ‘color: ‘ + name + ‘\tvalue: ‘+ hex + ‘\tstyle: ‘ + style
    insert_color = ("INSERT INTO COLOR(Color,Value,Style)" "VALUES(%s,%s,%s)")
    data_color = (name, hex, style)
    cursor.execute(insert_color, data_color)
    db.commit()
    # print ‘******完成此條插入!‘

print (‘爬取數據並插入mysql數據庫完成...‘)

5 運行這個代碼 ptyhon demo3.py

6 看看運行的結果

7 數據庫裏面看看結果

支持完成，成功，等會抓個別的例子 練練手

python第一個爬蟲的例子抓取數據到mysql，實測有數據