Python3爬虫入门之爬取豆瓣Top250电影名称

Python3爬虫入门之爬取豆瓣Top250电影名称

准备工具

• Python3.5
• requests
• BeautifulSoup
• lxml

最终效果

• 首先看一下网站的结构
  
  可以很清楚的看到每个电影对应了一个
• 标签，我们只需要一步一步的从
  向下搜索，可以得到电影对应的名称，即肖申克的救赎 这一行
  1. 接着看一下网页内 后页按钮对应的代码结构
     
     可以看出后一页的URL为 https://movie.douban.com/top250?start=25&filter= 最后一页这没有这个标签 对应None
     这样我们就可以进行翻页了
     直接上代码
  2. 获取html代码
     这里使用requests模块，获取很方便

import requests

# 获取目标网页html
def download_page(url):
# 伪装成浏览器
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
    }
    data = requests.get(url, headers=headers).content
    return data

• 解析html
  获取到html源码后就要对其进行解析了，这里使用BeautifulSoup模块

from bs4 import BeautifulSoup
URL='https://movie.douban.com/top250'

# 解析html 方法一  (这里的写法参考了某博主的代码)
def parse_html(html):
    # 获取BeautifulSoup 对象
    soup = BeautifulSoup(html,'lxml')
    movie_name_list = []
    # 先获取最外层ol
    movie_list_soup = soup.find('ol', attrs={'class':'grid_view'})
    # 获取每个列表

    for movie_li in movie_list_soup.find_all('li'):
        detail = movie_li.find('div', attrs={'class':'hd'})
        movie_name = detail.find('span', attrs={'class':'title'}).getText()# 这里名称要用getText()获取相应内容
        movie_name_list.append(movie_name)
    next_page = soup.find('span',attrs={'class':'next'}).find('a')
    if next_page:
        return movie_name_list,URL+next_page['href']
    return movie_name_list,None

from bs4 import BeautifulSoup
URL='https://movie.douban.com/top250'


# 解析html方法2 这里用了一些BeautifulSoup的新特性 用起来比较方便
def parse_html1(html):
    soup = BeautifulSoup(html, 'lxml');
    movie_names = []
    movie_list = soup.select('ol.grid_view li div.item div.info div.hd a')
    for movie_title in movie_list:
        movie_name = movie_title.find('span',class_='title')
        movie_names.append(movie_name.getText())
    next_page = soup.find('span',class_='next').find('a')
    if next_page:
        return movie_names,URL+next_page['href']
    return movie_names,None

• 汇总一下，并把获取到的名字列表写进文件中

import requests
from bs4 import BeautifulSoup
URL='https://movie.douban.com/top250'


# 获取目标网页html
def download_page(url):
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
    }
    data = requests.get(url, headers=headers).content
    return data
# 解析html
def parse_html1(html):
    soup = BeautifulSoup(html, 'lxml');
    movie_names = []
    movie_list = soup.select('ol.grid_view li div.item div.info div.hd a')
    for movie_title in movie_list:
        movie_name = movie_title.find('span',class_='title')
        movie_names.append(movie_name.getText())
    next_page = soup.find('span',class_='next').find('a')
    if next_page:
        return movie_names,URL+next_page['href']
    return movie_names,None


def main():
    url = URL
    with codecs.open('e:/movies.txt','wb',encoding='utf-8') as fp:
        while url:
            html = download_page(url)
            movies,url=parse_html1(html)
            for movie_name in movies:
                fp.write(movie_name)
                fp.write('\r\n')
if __name__=='__main__':
    main()