摘要：準備工作運行本地數據庫服務器安裝建表連接數據庫用操作還是比較簡單的，如果有一點數據庫基礎的話，可以直接上手，最后一定不要忘了寫提交，不然數據只是緩存，存不到數據庫里完整示例爬取百度上最熱的幾個新聞標題，并存儲到數據庫，太懶了沒寫注釋

運行本地數據庫服務器

    mysql -u root -p

安裝pymysql

    pip install pymysql

CREATE DATABASE crawls;
// show databases; 
use db;

CREATE TABLE IF NOT EXISTS baiduNews("
       "id INT PRIMARY KEY NOT NULL AUTO_INCREMENT,"
       "ranking VARCHAR(30),"
       "title VARCHAR(60),"
       "datetime TIMESTAMP,"
       "hot VARCHAR(30));
// show tables;

db = pymysql.connect(host="localhost", port=3306, user="root", passwd="123456", 
                    db="crawls", charset="utf8")
cursor = db.cursor()
cursor.execute(sql_query)
db.commit()

用python操作mysql還是比較簡單的，如果有一點數據庫基礎的話，可以直接上手，最后一定不要忘了寫commit提交，不然數據只是緩存，存不到數據庫里

爬取百度上最熱的幾個新聞標題，并存儲到數據庫，太懶了沒寫注釋-_- (確保本地mysql服務器已經打開）

"""
Get the hottest news title on baidu page,
then save these data into mysql
"""
import datetime

import pymysql
from pyquery import PyQuery as pq
import requests
from requests.exceptions import ConnectionError

URL = "https://www.baidu.com/s?wd=%E7%83%AD%E7%82%B9"
headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36",
    "Upgrade-Insecure-Requests": "1"
}

def get_html(url):
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
        return None
    except ConnectionError as e:
        print(e.args)
        return None

def parse_html(html):
    doc = pq(html)
    trs = doc(".FYB_RD table.c-table tr").items()
    for tr in trs:
        index = tr("td:nth-child(1) span.c-index").text()
        title = tr("td:nth-child(1) span a").text()
        hot = tr("td:nth-child(2)").text().strip(""")
        yield {
            "index":index,
            "title":title,
            "hot":hot
        }

def save_to_mysql(items):
    try:
        db = pymysql.connect(host="localhost", port=3306, user="root", passwd="123456",
                             db="crawls", charset="utf8")
        cursor = db.cursor()
        cursor.execute("use crawls;")
        cursor.execute("CREATE TABLE IF NOT EXISTS baiduNews("
                       "id INT PRIMARY KEY NOT NULL AUTO_INCREMENT,"
                       "ranking VARCHAR(30),"
                       "title VARCHAR(60),"
                       "datetime TIMESTAMP,"
                       "hot VARCHAR(30));")
        try:
            for item in items:
                print(item)
                now = datetime.datetime.now()
                now = now.strftime("%Y-%m-%d %H:%M:%S")
                sql_query = "INSERT INTO baiduNews(ranking, title, datetime, hot) VALUES ("%s", "%s", "%s", "%s")" % (
                            item["index"], item["title"], now, item["hot"])
                cursor.execute(sql_query)
                print("Save into mysql")
            db.commit()
        except pymysql.MySQLError as e:
            db.rollback()
            print(e.args)
            return
    except pymysql.MySQLError as e:
        print(e.args)
        return

def check_mysql():
    try:
        db = pymysql.connect(host="localhost", port=3306, user="root", passwd="123456",
                             db="crawls", charset="utf8")
        cursor = db.cursor()
        cursor.execute("use crawls;")
        sql_query = "SELECT * FROM baiduNews"
        results = cursor.execute(sql_query)
        print(results)
    except pymysql.MySQLError as e:
        print(e.args)

def main():
    html = get_html(URL)
    items = parse_html(html)
    save_to_mysql(items)
    #check_mysql()

if __name__ == "__main__":
    main()