原因在于 证书信任和不做个伪装浏览器
import urllib.request
import re
from bs4 import BeautifulSoup
from distutils.filelist import findall
import ssl
# 信任所有Https的安全证书
ssl._create_default_https_context = ssl._create_stdlib_context
url_ = "http://movie.douban.com/top250?format=text"
header_ = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/51.0.2704.63 Safari/537.36'}
page = urllib.request.Request(url=url_, headers=header_)
page = urllib.request.urlopen(page)
contents = page.read()
# print(contents)
soup = BeautifulSoup(contents, "html.parser")
print("豆瓣电影TOP250" + "\n" + " 影片名 评分 评价人数 链接 ")
for tag in soup.find_all('div', class_='info'):
# print tag
m_name = tag.find('span', class_='title').get_text()
m_rating_score = float(tag.find('span', class_='rating_num').get_text())
m_people = tag.find('div', class_="star")
m_span = m_people.findAll('span')
m_peoplecount = m_span[3].contents[0]
m_url = tag.find('a').get('href')
print(m_name + " " + str(m_rating_score) + " " + m_peoplecount + " " + m_url)
