【爬虫】案例(爬取豆瓣top250)[完整＋详细]

流程** 使用requests库获取网页数据，使用bs4和re对网页进行解析和文字匹配最后使用xlwt和pymysql将数据存入excel和数据库**主函数from bs4 import BeautifulSoup# 网页解析，获取数据import re# 正则，文字匹配import requests# 获取网页数据import xlwt# excel操作import pymysql.cursor

可乐大牛

7209人浏览 · 2020-07-15 11:14:54

可乐大牛 · 2020-07-15 11:14:54 发布

文章目录

1、需求
2、流程
3、实现
5、完整代码
6、小注

1、需求

爬取豆瓣top250的电影的播放链接，封面链接，中外文名等数据，并作数据的持久化处理（存放到excel和数据库）

2、流程

使用requests库获取网页数据，使用bs4和re对网页进行解析和文字匹配
最后使用xlwt和pymysql将数据存入excel和数据库

3、实现

导包

# -*- coding: utf-8 -*
from bs4 import BeautifulSoup  # 网页解析，获取数据
import re       # 正则，文字匹配
import requests  # 获取网页数据
import xlwt     # excel操作
import pymysql.cursors      #   数据库操作

主函数

def main():
    baseUrl = "https://movie.douban.com/top250?start="
    # 爬取网页
    dataList = getDate(baseUrl)
    # 保存数据
    savePath = "豆瓣top250.xls"
    saveData(savePath, dataList)
    saveDataToDb(dataList)

数据获取

# 得到指定URL的网页内容
def askUrl(url):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36'
    }
    html = ""
    try:
        r = requests.get(url=url, headers=headers, timeout=3)
        r.encoding = 'utf-8'
        html = r.text
    except Exception as e:
        if hasattr(e, "code"):
            print(e.code)
        if hasattr(e, "reason"):
            print(e.reason)
    return html

数据解析

def getDate(baseUrl):
    dataList = []
    for i in range(0, 10):
        url = baseUrl + str(i*25)
        html = askUrl(url)
        # 解析数据
        soup = BeautifulSoup(html, "html.parser")
        for item in soup.find_all("div", class_="item"):
            data = []  # 存放一部电影的所有信息
            item = str(item)
            link = re.findall(r'<a href="(.*)">', item)[0]  # 链接
            data.append(link)
            image = re.findall(r'<img.*src="(.*)" .*/>', item)[0]  # 图片
            data.append(image)
            titles = re.findall(r'<span class="title">(.*)</span>', item)  # 片名
            data.append(titles[0])   # 添加中文名
            if len(titles) == 2:   # 添加外国名
                data.append(titles[1].replace("\\", ""))
            else:
                data.append(" ")
            rate = re.findall(r'<span class="rating_num".*>(.*)</span>', item)[0]  # 评分
            data.append(rate)
            judge = re.findall(r'<span>(\d*)人评价</span>', item)[0]  # 评级人数
            data.append(judge)
            inq = re.findall(r'<span class="inq">(.*)</span>', item, re.S)  # 简述
            if len(inq) != 0:
                inq = inq[0].replace("。", "")
                data.append(inq)
            else:
                data.append("")
            bd = re.findall(r'<p class="">(.*?)</p>', item,  re.S)[0]    # 其他信息
            bd = re.sub('<br/>', " ", bd)
            bd = re.sub("/", " ", bd)
            bd = re.sub("\\n", " ", bd)
            bd = re.sub(r"\xa0", " ", bd)
            data.append(bd.strip())
            dataList.append(data)
    return dataList

存储到excel

def saveData(savePath, dataList):
    workbook = xlwt.Workbook(encoding="utf-8", style_compression=0)
    worksheet = workbook.add_sheet("豆瓣top250", cell_overwrite_ok=True)
    col = ("电影详情链接", "图片链接", "影片中文名", "影片英文名", "评分", "评价数", "概况", "相关信息")
    for i in range(0, 8):
        worksheet.write(0, i, col[i])
    for i in range(0, 250):
        data = dataList[i]
        for j in range(0, 8):
            worksheet.write(i+1, j, data[j])
    workbook.save(savePath)

简易数据库

DROP TABLE IF EXISTS `top250`;
CREATE TABLE `top250` (
  `id` int(11) NOT NULL AUTO_INCREMENT,
  `link` varchar(255) DEFAULT NULL,
  `image` varchar(255) DEFAULT NULL,
  `cname` varchar(255) DEFAULT NULL,
  `oname` varchar(255) DEFAULT NULL,
  `rate` varchar(255) DEFAULT NULL,
  `judge` varchar(255) DEFAULT NULL,
  `inq` varchar(255) DEFAULT NULL,
  PRIMARY KEY (`id`)
) ENGINE=InnoDB AUTO_INCREMENT=517 DEFAULT CHARSET=utf8;

存储到数据库

def saveDataToDb(dataList):
    for i in range(0, len(dataList)):
        data = dataList[i]
        print(data)
        # 连接数据库
        connect = pymysql.Connect(
            host='localhost',
            port=3306,
            user='root',
            passwd='',
            db='douban',
            charset='utf8'
        )
        # 获取游标
        cursor = connect.cursor()
        sql = "INSERT INTO top250 (link, image, cname, oname, rate, judge, inq) VALUES (  '%s', '%s', '%s', '%s', '%s', '%s', '%s')"
        data = (data[0], data[1], data[2], data[3], data[4], data[5], data[6])
        cursor.execute(sql % data)
        connect.commit()

5、完整代码

# -*- coding: utf-8 -*
from bs4 import BeautifulSoup  # 网页解析，获取数据
import re       # 正则，文字匹配
import requests  # 获取网页数据
import xlwt     # excel操作


def main():
    baseUrl = "https://movie.douban.com/top250?start="
    # 爬取网页
    dataList = getDate(baseUrl)
    # 保存数据
    savePath = "豆瓣top250.xls"
    saveData(savePath, dataList)
    # saveDataToDb(dataList)

# 得到指定URL的网页内容
def askUrl(url):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36'
    }
    html = ""
    try:
        r = requests.get(url=url, headers=headers, timeout=3)
        r.encoding = 'utf-8'
        html = r.text
    except Exception as e:
        if hasattr(e, "code"):
            print(e.code)
        if hasattr(e, "reason"):
            print(e.reason)
    return html

def getDate(baseUrl):
    dataList = []
    for i in range(0, 10):
        url = baseUrl + str(i*25)
        html = askUrl(url)
        # 解析数据
        soup = BeautifulSoup(html, "html.parser")
        for item in soup.find_all("div", class_="item"):
            data = []  # 存放一部电影的所有信息
            item = str(item)
            link = re.findall(r'<a href="(.*)">', item)[0]  # 链接
            data.append(link)
            image = re.findall(r'<img.*src="(.*)" .*/>', item)[0]  # 图片
            data.append(image)
            titles = re.findall(r'<span class="title">(.*)</span>', item)  # 片名
            data.append(titles[0])   # 添加中文名
            if len(titles) == 2:   # 添加外国名
                data.append(titles[1].replace("\\", ""))
            else:
                data.append(" ")
            rate = re.findall(r'<span class="rating_num".*>(.*)</span>', item)[0]  # 评分
            data.append(rate)
            judge = re.findall(r'<span>(\d*)人评价</span>', item)[0]  # 评级人数
            data.append(judge)
            inq = re.findall(r'<span class="inq">(.*)</span>', item, re.S)  # 简述
            if len(inq) != 0:
                inq = inq[0].replace("。", "")
                data.append(inq)
            else:
                data.append("")
            bd = re.findall(r'<p class="">(.*?)</p>', item,  re.S)[0]    # 其他信息
            bd = re.sub('<br/>', " ", bd)
            bd = re.sub("/", " ", bd)
            bd = re.sub("\\n", " ", bd)
            bd = re.sub(r"\xa0", " ", bd)
            data.append(bd.strip())
            dataList.append(data)
    return dataList

def saveData(savePath, dataList):
    workbook = xlwt.Workbook(encoding="utf-8", style_compression=0)
    worksheet = workbook.add_sheet("豆瓣top250", cell_overwrite_ok=True)
    col = ("电影详情链接", "图片链接", "影片中文名", "影片英文名", "评分", "评价数", "概况", "相关信息")
    for i in range(0, 8):
        worksheet.write(0, i, col[i])
    for i in range(0, 250):
        data = dataList[i]
        for j in range(0, 8):
            worksheet.write(i+1, j, data[j])
    workbook.save(savePath)

if (__name__ == "__main__"):
    main()