01_豆瓣

序言

2017，定下一个小目标，深度学Python~

爬取对象

抓取豆瓣电影Top250

使用包

import codecs  #非必须，用于指定创建记录爬取文件字符集
import requests #数据抓取
from bs4 import BeautifulSoup #抓取内容解析

实现步骤

1、编写抓取伪代码

url = 'https://www.douban.com/'
webPage = requests.get(url).text
soup = BeautifulSoup(webPage,"html.parser")
print(soup.title)  # 

2、抓取对象分析

• 通过F12捕获页面内容得知待抓取内容以列表形式显示在grid_view中，每“行”主要分为左侧图片、右侧电影名称等文本介绍
  
  

  肖申克的救赎
• 分析翻页机制，重点关注不同页间URL区别
  
  

  翻页

3、电影名称抓取实现

import codecs  #非必须，用于指定创建记录爬取文件字符集
import requests #数据抓取
from bs4 import BeautifulSoup #抓取内容解析

DOWNLOAD_URL = 'http://movie.douban.com/top250/'

def download_page(url):
    return requests.get(url, headers={
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.80 Safari/537.36'
    }).content

def parse_html(html):
    soup = BeautifulSoup(html, "html.parser")
    movie_list_soup = soup.find('ol', attrs={'class': 'grid_view'})

    movie_name_list = []

    print("当前准备解析页码：" + soup.find('span', attrs={'class': 'thispage'}).getText())

    top_num = 1 + (int(soup.find('span', attrs={'class': 'thispage'}).getText())-1) * 25

    for movie_li in movie_list_soup.find_all('li'):
        detail = movie_li.find('div', attrs = {'class': 'hd'})

        movie_name_list.append("## Top " + str(top_num))

        #名称
        movie_name = ""

        for sp in detail.find_all('span', attrs={'class': 'title'}):
            movie_name += sp.text

        img = movie_li.find('div', attrs={'class': 'pic'}).find('a').find('img')

        movie_name_list.append("### "+ movie_name )

        top_num +=1

    next_page = soup.find('span', attrs={'class': 'next'}).find('a')

    if next_page:
        return movie_name_list, DOWNLOAD_URL + next_page['href']
    return movie_name_list, None

def main():
    url = DOWNLOAD_URL

    with codecs.open('douban_moviesList_top250.md', 'wb', encoding='utf-8') as fp:
        while url:
            html = download_page(url)
            movies, url = parse_html(html)
            fp.write(u'{movies}\n'.format(movies='\n'.join(movies)))

if __name__ == '__main__':
    main()

电影名称

4、基于名称，补充剩余信息解析

• 封面解析示意

        img = movie_li.find('div', attrs={'class': 'pic'}).find('a').find('img')
        
        try:
            img_req = requests.get(img["src"], timeout=20)
            img_localhost = 'douban_moviesList_top250\\'+str(top_num)+ '.jpg'
            with open(img_localhost, 'wb') as f:
                f.write(img_req.content)

            movie_name_list.append('![](douban_moviesList_top250/'+str(top_num)+'.jpg "douban_moviesList_top250")')
            
        except requests.exceptions.ConnectionError:
            print('【错误】当前图片无法下载，失效地址为：' + img["src"])

总结

因豆瓣大部分均为静态页面，相对较为简单，主要涉及翻页循环、图片抓取异常处理、BeautifulSoup 中 find、find_all使用......
好了，到此结束，我是不会承认我会抓取豆瓣妹子什么的......
完整代码

豆瓣Top250