爬虫爬取猫眼电影TOP10的电影信息

最新推荐文章于 2022-09-05 13:53:46 发布

原创

最新推荐文章于 2022-09-05 13:53:46 发布 · 置顶 · 619 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#python #正则表达式 #url #html

“”"
爬取猫眼电影TOP10的电影信息
“”"
from urllib import request
import re
import time
import random
from fake_useragent import UserAgent

class MaoyanSpider(object):
def init(self):
self.url = ‘https://maoyan.com/board/4?offset={}’

def get_html(self,url):
    headers = { 'User-Agent': UserAgent().random }
    res = request.Request(url=url,headers=headers)
    resp = request.urlopen(res)
    html = resp.read().decode()
    self.parse_html(html)

def parse_html(self,html):
    regex = '<div class="movie-item-info">.*?title="(.*?)".*?class="star">(.*?)</p>.*?releasetime">(.*?)</p>'
    pattern = re.compile(regex,re.S)
    dd_list = pattern.findall(html)
    self.save_html(dd_list)
def save_html(self,dd_list):
    item = {}
    for dd in dd_list:
        item['name'] = dd[0].strip()
        item['star'] = dd[1].strip()
        item['time'] = dd[2].strip()
        print(item)

def run(self):
    for o