import urllib.request
import re
from bs4 import BeautifulSoup
import sqlite3
import xlwt
def main():
baseurl = "https://movie.douban.com/top250?start="
#1.爬取网页
datalist = getData(baseurl)
savepath = ".\\豆瓣电影Top250.xls"
dbpath = ".\\豆瓣电影Top250.db"
#3.保存数据
saveData(datalist,savepath)
#4.保存数据到数据库
saveData2DB(datalist,dbpath)
#影片详情链接的规则
findlink = re.compile(r'<a href="(.*?)">')
#影片图片
findImgScr = re.compile(r'<img.*src="(.*?)"/>' ,re.S) #让换行符包含在字符中
#影片片名
findTitle = re.compile(r'<span class="title">(.*)</span>')
#影片评分
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
#评价人数
findJudge = re.compile(r'<span>(\d*)人评价</span>')
#找到概况
findInq = re.compile(r'<span class="inq">(.*)</span>')
#找到影片相关内容
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)
#1.爬取网页
def getData(baseurl):
datalist = []
for i in range(0,10):
url = baseurl + str(i*25)
html = askURL(url)
#2.逐一解析
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
data = [] #保存一部电影的所有信息
item = str(item)
# 影片详情链接
link = re.findall(findlink,item)[0]
data.append(link) #在data列表中添加链接
#影片图片
ImgScr = re.findall(findImgScr,item)[0]
data.append(ImgScr) #在data列表中添加图片
#影片片名
titles = re.findall(findTitle,item) #片名可能只有一个中文名，没有外文名
if len(titles)==2:
ctitle = titles[0]
data.append(ctitle) #添加中文名
otitle = titles[1].replace("/","") #去掉无关符号
data.append(otitle) #添加外国名
else:
data.append(titles[0])
data.append("") #外国名字留空
#影片评分
rating = re.findall(findRating,item)[0]
data.append(rating)
#评价人数
judge = re.findall(findJudge,item)[0]
data.append(judge)
#找到概况
inq = re.findall(findInq,item)
if len(inq) != 0:
inq = inq[0].replace("。","")
data.append(inq)
else:
data.append(" ")
#找到影片相关内容
bd = re.findall(findBd,item)[0]
bd = re.sub('<br(\s+)?/>(\s+)?', "", bd) #去掉<br>
bd = re.sub('/'," ",bd) #去掉/
data.append(bd.strip()) #去掉前后的空格
datalist.append(data) #把处理好的一部电影信息放入datalist
print(datalist)
return datalist
#爬取指定一个网页
def askURL(url):
headers = {
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"
}
re = urllib.request.Request(url = url,headers = headers)
try:
response = urllib.request.urlopen(re)
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
#3.保存数据
def saveData(datalist,savepath):
book = xlwt.Workbook(encoding="utf-8",style_compression=0)
sheet = book.add_sheet('豆瓣电影Top250',cell_overwrite_ok=True)
col = ("电影详情链接","图片链接","影片中文名","影片外文名","评分","评价人数","影片概况","影片相关内容")
for i in range(0,8):
sheet.write(0,i,col[i]) #列名
for i in range(0,250):
print("第%d条"%(i+1))
data = datalist[i]
for j in range(0,8):
sheet.write(i+1,j,data[j]) #数据
book.save('豆瓣电影Top250.xls') #保存
#4.保存数据到数据库
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: #判断是否是评分或评价人数
continue
data[index] = '"'+data[index]+'"' #给data加双引号
sql = '''
insert into movie250(
info_link,pic_link,cname,ename,score,rated,inq,db)
values (%s)'''%",".join(data) #用“，”分隔data
cur.execute(sql)
conn.commit()
cur.close()
conn.close()
def init_db(dbpath):
conn = sqlite3.connect(dbpath)
cursor = conn.cursor()
sql = '''
create table movie250
(id integer primary key autoincrement,
info_link text,
pic_link text,
cname varchar,
ename varchar,
score numeric,
rated numeric,
inq text,
db text
)
'''#创建数据表
cursor.execute(sql)
conn.commit()
conn.close()
if __name__ == "__main__":#当程序执行时
main() #调用函数
print("爬取完毕！")
运行之后，打印了250遍sql语句，如下。怎么搞？崩溃了，卡在这两天了！
sql = '''
insert into movie250(
info_link,pic_link,cname,ename,score,rated,inq,db)
values (%s)'''%",".join(data)
