from bs4 import BeautifulSoup
import urllib.request,urllib.error
import re
import xlwt
#爬取网页
findLink = re.compile(r'<a href="(.*?)">')
findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S)
findTitle = re.compile(r'<span class="title">(.*)</span>')
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
findJudge = re.compile(r'<span>(\d*)</span>')
findInq = re.compile(r'<span class="inq">(.*?)</span>')
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)
def main():
baseurl="https://movie.douban.com/top250?start="
datalist=getDate(baseurl)
savepath=".\\豆瓣电影Top250.xls"
saveData(datalist,savepath)
def getDate(baseurl):
datalist = []
for i in range(0,10): #调用函数访问网页十次
url=baseurl + str(i*25)
html=askURL(url)
soup=BeautifulSoup(html,"html.parser")
for item in soup.find_all('div',class_='item'):
item=str(item)
data = []
link=re.findall(findLink,item)[0]
data.append(link)
ImgSrc = re.findall(findImgSrc,item)[0]
data.append(ImgSrc)
titles = re.findall(findTitle,item)
if len(titles) == 2:
ctitle = titles[0]
data.append(ctitle)
otitle = titles[1].replace("/","")
data.append(otitle)
else:
data.append(titles[0])
data.append(' ')
rating = re.findall(findRating,item)[0]
data.append(rating)
judgeNum = re.findall(findJudge,item)
data.append(judgeNum)
inq = re.findall(findInq,item)
if len(inq) != 0:
inq = inq[0].replace("。","")
data.append(inq)
else:
data.append(" ")
bd = str()
bd = re.findall(findBd,item)[0]
bd = re.sub('<br(\s+)?/>(\s+)?'," ",bd)
bd = re.sub('/',' ',bd)
data.append(bd.strip()) #去掉空格
datalist.append(data) #把处理好的一部电影的信息载入datalist
return datalist
def askURL(url):
head={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36 Edg/91.0.864.67"
}
request=urllib.request.Request(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
def saveData(datelist,savepath):
print("save......")
book = xlwt.Workbook(encoding='utf-8')
sheet = book.add_sheet('豆瓣电影Top250')
col = ("电影链接","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[i])
for i in range(0,250):
print("第%d条"%i)
data = datelist[i]
for j in range(0,8):
sheet.write(i+1,j,data[j])
book.save("student.xls")
if __name__ == '__main__':
main()