import pymssql #引入pymssql模块
import sys
from bs4 import BeautifulSoup # 网页解析，获取数据
import re # 正则表达式，进行文字匹配
import urllib.request, urllib.error # 制定URL,获取网页数据
import xlwt # 进行excel操作
def conn():
connect = pymssql.connect('(local)', 'ouou', '123456', 'MyRetile') #服务器名,账户,密码,数据库名
if connect:
print("连接成功!")
return connect
def main():
baseurl = "https://movie.douban.com/top250?start="
init_sql()
# 1.爬取网页
datalist = getData(baseurl)
savepath = r'.\\douban250.xls'
# 3.保存数据
# saveData(savepath,datalist)
saveDataSql(datalist)
def init_sql():
sql = '''
create table movie250
(id integer identity(1,1) primary key,
info_link text not null,
pic_link text not null,
cname varchar(80),
ename varchar(80),
score numeric,
rated numeric,
introduction text,
info text);
'''
conn = pymssql.connect('(local)', 'ouou', '123456', 'MyRetile',autocommit=True)
cursor = conn.cursor()
cursor.execute(sql)
conn.commit()
conn.close()
def saveDataSql(datalist):
thisconn = conn()
cur = thisconn .cursor()
for data in datalist:
for index in range(len(data)):
data[index] = data[index].replace("'", "''")
data[index] = '\'' + data[index] + '\''
sql = '''
insert into movie250(
info_link,pic_link,cname,ename,score,rated,introduction,info)
values(%s)
''' % ','.join(data)
print(sql)
cur.execute(sql)
thisconn.commit()
cur.close()
thisconn.close()
# 创建正则表达式对象，表示规则（字符串的模式）re.S 忽视换行符
# 1 影片详情链接的规则
findLink = re.compile(r'<a href="(.*?)">')
# 2 影片图片
findImgSrc = re.compile(r'<img.*src="(.*?)"', re.S)
# 3 影片片名
findTitle = re.compile(r'<span class="title">(.*)</span>')
# 4 影片评分
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
# 5 找到评价人数
findJudge = re.compile(r'<span>(\d*)人评价</span>')
# 6 找到概况
findInq = re.compile(r'<span class="inq">(.*)</span>')
# 7 找到影片的相关内容
findBd = re.compile(r'<p class="">(.*?)</p>', re.S)
cnt = 0
# 爬取网页
def getData(baseurl):
global cnt
datalist = []
for i in range(0, 10):
url = baseurl + str(i * 25)
html = askURL(url) # 保存获取到的网页源码
# 2.逐一解析数据
soup = BeautifulSoup(html, "html.parser")
for item in soup.find_all('div', class_='item'): # 查找符合要求的字符串，形成列表
# print(item)
data = []
item = str(item)
link = re.findall(findLink, item)[0]
data.append(link) # 添加连接
imgSrc = re.findall(findImgSrc, item)[0]
data.append(imgSrc) # 添加图片
titles = re.findall(findTitle, item) # 片名可能只有一个中文名，没有外国名
if (len(titles) == 2):
ctitle = titles[0] # 添加中文名
data.append(ctitle)
otitle = titles[1].replace("/", "") # 去掉无关的符号
data.append(otitle) # 添加外文名
else:
data.append(titles[0])
data.append(' ')
rating = re.findall(findRating, item)[0]
data.append(rating) # 添加图片
judgeNum = re.findall(findJudge, item)[0]
data.append(judgeNum) # 添加评价人数
inq = re.findall(findInq, item)
if len(inq) != 0:
inq = inq[0].replace("。", "") # 去掉句号
data.append(inq) # 添加概述
else:
data.append(" ")
bd = re.findall(findBd, item)[0]
bd = re.sub('<br(\s+)?/>(\s+)', " ", bd) # 去掉<br/>
bd = re.sub('/', ' ', bd) # 替换/
data.append(bd.strip())
datalist.append(data) # 把处理好的一部电影信息放入datalist
# cnt+=1
# print(str(cnt)+'.'+str(link))
# print(datalist)
return datalist
# 得到指定一个URL的网页内容
def askURL(url):
head = { # 模拟浏览器头部信息，向豆瓣服务器发送消息,下面一定不能写错！
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36'
}
# 用户代理，表示告诉豆瓣服务器，我们是什么类型的机器、浏览器（本质上是告诉浏览器，我们可以接收什么水平的文件内容）
request = urllib.request.Request(url=url, headers=head)
html = ''
try:
response = urllib.request.urlopen(request)
html = response.read().decode("utf-8")
# print(html)
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
return html
# 保存数据
def saveData(savepath, datalist):
# 创建workbook对象
workbook = xlwt.Workbook(encoding="utf-8")
# 创建工作表
worksheet = workbook.add_sheet('sheet1')
for i in range(0, 250):
for j in range(0, 8):
worksheet.write(i, j, datalist[i][j])
workbook.save(savepath)
if __name__ == '__main__':
main()
