爬取豆瓣TOP电影各个电影的链接
from bs4 import BeautifulSoup
import urllib.request,urllib.error
import re
#爬取网页
findLink = re.compile(r'<a href="(.*?)">')
def main():
baseurl="https://movie.douban.com/top250?start="
datalist=getDate(baseurl)
#savepath=".\\豆瓣电影Top250.xls"
def getDate(baseurl):
datalist = []
for i in range(0,1): #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)
link=re.findall(findLink,item)[0]
print(link)
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
if __name__ == '__main__':
main()