1.保存数据到excel中
import xlwt
workbook=xlwt.Workbook(encoding="utf-8")
worksheet=workbook.add_sheet('sheet1')
worksheet.write(0,0,'你好~')
workbook.save('first.xls')
创建位置默认是同级目录下
from bs4 import BeautifulSoup
import re
import urllib.request,urllib.error
import xlwt
import _sqlite3
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*)人评价</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=getData(baseUrl)
savePath="豆瓣电影.xls"
saveData(dataList,savePath)
def getData(baseUrl):
dataList = []
for i in range(0,10):
url=baseUrl+str(i*25)
html=askURL(url)
soup=BeautifulSoup(html,"html.parser")
for item in soup.find_all('div',class_="item"):
data=[]
item=str(item)
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)[0]
data.append(judgeNum)
inq=re.findall(findInq,item)
data.append(inq)
if len(inq)!=0:
data.append(inq)
else:
data.append(" ")
bd = re.findall(findBd, item)[0]
bd = re.sub('<br(1s+)?/>(ls+)?', " ", bd)
bd = re.sub('/', " ", bd)
data.append(bd.strip())
dataList.append(data)
return dataList
def askURL(url):
head={
"User-Agent": "Mozilla / 5.0(Windows NT 10.0;WOW64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36 SLBrowser/7.0.0.4071 SLBChan/21"
}
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
def saveData(dataList,savePath):
print("正在执行保存数据")
book=xlwt.Workbook(encoding="utf-8",style_compression=0)
sheet=book.add_sheet('豆瓣电影Top250',cell_overwrite_ok=True)
col=("电影链接","图片链接","电影中文名","电影外国名","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+1))
data=dataList[i]
for j in range(0,8):
sheet.write(i+1,j,data[j])
book.save(savePath)
if __name__ =="__main__":
main()