python爬虫练习
第一次尝试，用的PyCharm不是很熟练，社区版也没搞懂数据库怎么用，就只能用excel保存了# -*-codeing = utf-8 -*-
# @Time : 2021/10/1 15:57
# @Author : 有点冷丶
# @File : pachong.py
# @Software: PyCharm
#引入模块
from bs4 import BeautifulSoup #网页解析
import re #正则表达式，文字匹配
import urllib.request #制定upl，获取网页数据
import urllib.error
import xlwt #进行excel操作
import sqlite3 #进行sqlite数据库操作
def main():
baseurl = "http://movie.douban.com/top250?start="
#1.爬取网页
datalist = getData(baseurl)
#3.保存数据
savepath = r".\\豆瓣电影top250.xls"
saveData(datalist,savepath) #保存到excel表格
dppath = "movie250.db"
#savedata2db(datalist,dbpath) #保存到数据库
#影片详情链接规则
findLink = re.compile(r'<a href="(.*?)">')#创建正则表达式对象，表示规则，字符串模式
#影片图片的链接
findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S)
#影片的片名
findname = re.compile(r'<span class="title">(.*?)</span>')
#影片的评分
finddafen = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
#评价人数
findpeople = re.compile(r'<span>(\d*)人评价</span>')
#找到概况
findInq = re.compile(r'<span class="inq">(.*)</span>')
#相关内容
finddy = re.compile(r'<p class="">(.*?)</p>',re.S)
#爬取网页
def getData(baseurl):
datalist = []
for i in range(0,1): #调用获取页面
url = baseurl + str(i*25)
html = askURL(url) #保存获取到的网页源码
#print(html)
# 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) #测试查看电影全部item信息
data = [] #保存一个电影的全部信息
item = str(item)
#影片详情超链接
link = re.findall(findLink,item) #re库
data.append(link) #添加链接
imgSrc = re.findall(findImgSrc,item)
data.append(imgSrc) #添加图片
names = re.findall(findname,item)
if(len(names) == 2):
cname = names #添加中文名
data.append(cname)
oname = names.replace("/","") #去掉无关的符号
data.append(oname) #添加外国名
else:
data.append(names)
data.append('') #外国名留空
dafen = re.findall(finddafen,item)
data.append(dafen) #添加评分
people = re.findall(findpeople,item)
data.append(people) #添加打分人数
inq = re.findall(findInq,item) #添加概况
if len(inq) != 0:
inq = inq.replace("。","")
data.append(inq)#添加概述
else:
data.append("")#留空
dy = re.findall(finddy,item)#添加相关内容
dy = re.sub('<br(\s+)?/>(\s+)?'," ",dy)
dy = re.sub('/'," ",dy)
data.append(dy.strip()) #strip去掉前后空格
datalist.append(data) #把处理好的信息储存进datalist
#print(datalist, "\n")
return datalist
#得到指定一个url的网页的内容
def askURL(url):
head = {
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36 Edg/94.0.992.31"
}
#用户代理，伪装
request = urllib.request.Request(url,headers=head)
html = ""
try:
response = urllib.request.urlopen(request)
html = response.read().decode("utf-8")
except urllib.error.URLError as e:
if hasattr(e,"code"):
print(e.code)
if hasattr(e,"reason"):
print(e.reason)
return html
#保存数据到excel
def saveData(datalist,savepath):
print("save...")
book = xlwt.Workbook(encoding="utf-8",style_compression=0)# 创建一个workbook对象
sheet = book.add_sheet('豆瓣电影top250',cell_overwrite_ok=True)# 创建工作表
col = ("电影详情链接","图片链接","影片中文名","影片外国名","评分","评价数","概况","相关信息")
for i in range(0,8):
sheet.write(0,i,col)#列名
for i in range(0,250):
print("第%d条"%(i+1))
data = datalist
for j in range(0,8):
sheet.write(i+1,j,data)
book.save(savepath)# 保存数据表
#保存到数据库
def savedata2db(datalist,dbpath):
init_db(dbpath)
conn = sqlite3.connect(dbpath)
cur = conn.cursor()
for data in datalist:
for index in range(len(data)):
if index == 4 or index == 5:
continue
data = '"'+data+'"'
sql = '''
insert into movie250(
info_link,pic_link,cname,ename,score,rated,introduction,info)
values(%s)'''%",".join(data)
cur.execute(sql)
conn.commit()
cur.close()
conn.close()
#创建数据库
def init_db(dbpath):
sql = '''
create table movie250
(
id integer primary key autoincrement,
info_link text,
pic_link text,
cname varchar,
ename varchar,
score numeric,
rated numeric,
introduction text,
info text
)
'''
conn = sqlite3.connect(dbpath)
cursor = conn.cursor()
cursor.execute(sql)
conn.commit()
conn.close()
if __name__ == "__main__":
main()
#init_db("test.db") #测试数据库
print("爬取完毕") pycharm社区版本不支持大部分第三方库
页:
[1]