附: Python爬虫 数据库保存数据

原文

1.笔记

#-*- codeing = utf-8 -*-
#@Time : 2020/7/15 22:49
#@Author : HUGBOY
#@File : hello_sqlite3.py
#@Software: PyCharm
'''---------------|Briefing|------------------
sqlite3
——a new way to save data !
------------------------------------'''

import sqlite3

#连接

print("Connect code:")
# conn = sqlite3.connect("sql.database")#创建/打开数据库文件
#
# c = conn.cursor()#获取游标
#
# sql = '''
# create table company
#     (id int primary key not null,
#     name text not null,
#     age int not null,
#     address char(58),
#     salary real);
# ''' #三个点多行语句
#
# #第一次创建 c.execute(sql)#执行sql语句
#
# conn.commit()#提交保存
#
# print("建表成功！")
#
# conn.close()#关闭数据库

2.实例

效果

原码

#-*- codeing = utf-8 -*-
#@Time : 2020/7/16 12:12
#@Author : HUGBOY
#@File : sp_douban2(sql).py
#@Software: PyCharm
# -*- codeing = utf-8 -*-
# @Time : 2020/7/12 19:11
# @Author : HUGBOY
# @File : sp_douban1(excel).py
# @Software: PyCharm
'''----------------------|简介|------------------
#爬虫
#爬取豆瓣TOP250电影数据
#1.爬取网页
#2.逐一解析数据
#3.保存数据
----------------------------------------------'''

from bs4 import BeautifulSoup  # 网页解析、获取数据
import re  # 正则表达式
import urllib.request, urllib.error  # 指定URL、获取网页数据
import random
import xlwt  # 存到excel的操作
import sqlite3  # 存到数据库操作
import os
from urllib.request import urlretrieve#保存电影海报图

def main():
    baseurl = "https://movie.douban.com/top250/?start="
    datalist = getdata(baseurl)
    #savepath = ".\\豆瓣电影Top250_data.xls"
    #savedata(datalist,savepath)
    dbpath = ("豆瓣电影Top250_data.db")
    savedata(datalist,dbpath)
# 正则表达式匹配规则

findTitle = re.compile(r'<span class="title">(.*)</span>')  # 影片片名
findR = re.compile(r'<span class="inq">(.*)</span>')  # 一句话评
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')  # 影片评分
findPeople = re.compile(r'<span>(\d*)人评价</span>')  # 影评人数-/d 代表数字
findLink = re.compile(r'<a href="(.*?)">')  # 影片链接
findImg = re.compile(r'<img.*src="(.*?)"', re.S)  # 影片图片-re.S 允许.中含换行符
findBd = re.compile(r'<p class="">(.*?)</p>', re.S)  # 影片简介

def getdata(baseurl):
    datalist = []
    getimg = 0
    for i in range(0, 10):  # 调用获取页面信息的函数*10次
        url = baseurl + str(i * 25)
        html = askURL(url)  # 保存获取到的网页原码
        # 解析网页
        soup = BeautifulSoup(html, "html.parser")
        for item in soup.find_all('div', class_="item"):
            # print(item) #一部电影的所有信息
            data = []
            item = str(item)
            # 提取影片详细信息

            title = re.findall(findTitle, item)
            if (len(title) == 2):
                ctitle = title[0]  # 中文名
                data.append(ctitle)
                otitle = title[1].replace("/", "")  # 外文名-去掉'/'和""
                data.append(otitle)
            else:
                data.append(title[0])
                data.append("无外文名")
            img = re.findall(findImg, item)[0]
            data.append(img)
            '''--------------------
            爬取图片
            --------------------'''
            os.makedirs('./movie_img/', exist_ok=True)#创建保存目录
            getimg+=1
            str_getimg = str(getimg)
            #格式 urlretrieve(IMAGE_URL, './img/image1.png')
            urlretrieve(img, './movie_img/img'+str_getimg+'.png')
            link = re.findall(findLink, item)[0]  # re库：正则表达式找指定字符串
            data.append(link)
            rating = re.findall(findRating, item)[0]
            data.append(rating)
            people = re.findall(findPeople, item)[0]
            data.append(people)
            r = re.findall(findR, item)
            if len(r) != 0:
                r = r[0].replace("。", "")
                data.append(r)
            else:
                data.append("无一句评")

            bd = re.findall(findBd, item)[0]
            bd = re.sub('<br(\s+)?/>(\s+)?', " ", bd)  # 替换</br>
            bd = re.sub('/', " ", bd)  # 替换/
            data.append(bd.strip())  # 去掉空格

            datalist.append(data)  # 把一部电影信息存储

    #print(datalist)
    return datalist

# 得到指定Url网页内容
def askURL(url):

    head = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101 Firefox/78.0"}
    request = urllib.request.Request(url, headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        #print(html) 测试
    except Exception as rel:
        if hasattr(rel, "code"):
            print(rel.code)
        if hasattr(rel, "reason"):
            print(rel.reason)
    return html

def savedata(datalist,dbpath):
    print("save data in sql ...")
    create_db(dbpath)
    conn = sqlite3.connect(dbpath)
    c = conn.cursor()

    for data in datalist:
        for index in range(len(data)):
            if index==4 or index==5:#score rated 类型为numeric
                continue
            data[index]='"'+data[index]+'"'
        sql = '''
            insert into movie_T250
            (
            name,fname,img_link,film_link,score,rated,one_cont,instroduction
            )
            values(%s)'''%",".join(data)
        c.execute(sql)
        conn.commit()
    c.close()
    conn.close()

def create_db(dbpath):
    sql='''
        create table movie_T250
        (
        id integer primary key autoincrement,
        name varchar,
        fname varchar,
        img_link text,
        film_link text,
        score  numeric,
        rated numeric,
        one_cont text,
        instroduction text
        );
        '''
    conn = sqlite3.connect(dbpath)
    c = conn.cursor()
    c.execute(sql)
    conn.commit()
    c.close()
    print("create table success !")

if __name__ == "__main__":
    main()
    print("爬取完成，奥利给！")