用Python爬取豆瓣电影链接，为何爬下来的链接总是重复出现两次

Question

from urllib.request import urlopen
from bs4 import BeautifulSoup
import re

html = urlopen("https://movie.douban.com/")
bsobj = BeautifulSoup(html)
for titles in bsobj.findAll("li",{"class":"title"}):
print(titles.get_text())

for link in bsobj.findAll("a",href = re.compile("https://movie.douban.com/subject/.*/?from=showing")):
if 'href' in link.attrs:
print(link.attrs['href'])

Answer 1

因为图片和标题都有链接，所以加一个条件筛选

from urllib.request import urlopen
from bs4 import BeautifulSoup
import re
html = urlopen("https://movie.douban.com/")
bsobj = BeautifulSoup(html)
for titles in bsobj.findAll("li",{"class":"title"}):
    print(titles.get_text())
for link in bsobj.findAll("a",{"onclick":"moreurl(this, {from:'mv_a_pst'})"},href = re.compile("https://movie.douban.com/subject/.*/?from=showing")):
    if 'href' in link.attrs:
        print(link.attrs['href'])