Python爬取網頁上想要的資料
阿新 • • 發佈:2022-04-07
原始碼如下
from urllib.request import urlopen,Request
import urllib.request
import re
from bs4 import BeautifulSoup
from distutils.filelist import findall
url ='http://movie.douban.com/top250?format=text'
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.60 Safari/537.36 '}
ret = Request(url,headers=headers)
page = urllib.request.urlopen(ret)
contents = page.read()
# print(contents)
soup = BeautifulSoup(contents, "html.parser")
print("豆瓣電影TOP250" + "\n" + " 影片名 評分 評價人數 連結 ")
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)