豆瓣影评数据抓取

抓取豆瓣影评评分

正常的抓取

• 分析请求的url

https://movie.douban.com/subject/26322642/comments?start=20&limit=20&sort=new_score&status=P&percent_type=

里面有用的也就是start和limit参数，我尝试过修改limit参数，但是没有效果，可以认为是默认的
start参数是用来设置从第几条数据开始查询的

• 设计查询列表，发现页面中有url中的查询部分，且指向下一个页面

于是采用下面的代码进行判断是否还有下一个页面

if next_url:
        visit_URL('https://movie.douban.com/subject/24753477/comments'+next_url)

• 用requests发送请求，beautifulsoup进行网页解析
  

• 把数据写入txt

import requests
from bs4 import BeautifulSoup


first_url = 'https://movie.douban.com/subject/26322642/comments?status=P'


# 请求头部
headers = {
    'Host':'movie.douban.com',
    'Referer':'https://movie.douban.com/subject/24753477/?tag=%E7%83%AD%E9%97%A8&from=gaia_video',
    'Upgrade-Insecure-Requests':'1',
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36',
}

def visit_URL(url):
    res = requests.get(url=url,headers=headers)
    soup = BeautifulSoup(res.content,'html5lib')
    div_comment = soup.find_all('div',class_='comment-item') # 找到所有的评论模块
    for com in div_comment:
        username = com.find('div',class_='avatar').a['title']
        comment_time = com.find('span',class_='comment-time')['title']
        votes = com.find('span',class_='votes').get_text()
        comment = com.p.get_text()
        with open('1.txt','a',encoding='utf8') as file:
            file.write('评论人：'+username+'\n')
            file.write('评论时间：'+comment_time+'\n')
            file.write('支持人数：'+votes+'\n')
            file.write('评论内容：'+comment+'\n')

    # 检查是否有下一页
    next_url = soup.find('a',class_='next')
    if next_url:
        temp = next_url['href'].strip().split('&') # 获取下一个url
        next_url = ''.join(temp)
        print(next_url)
    # print(next_url)
    if next_url:
        visit_URL('https://movie.douban.com/subject/24753477/comments'+next_url)


if __name__ == '__main__':
    visit_URL(first_url)

模仿移动端

很多时候模仿移动端获得的页面会比PC端的简单，更加容易解析，这次模拟移动端，发现可以直接访问api获取json格式的数据，nice!

至于怎么模拟移动端只需要将user-agent修改为移动端的头

useragents = [
    "Mozilla/5.0 (iPhone; CPU iPhone OS 9_2 like Mac OS X) AppleWebKit/601.1 (KHTML, like Gecko) CriOS/47.0.2526.70 Mobile/13C71 Safari/601.1.46",
    "Mozilla/5.0 (Linux; U; Android 4.4.4; Nexus 5 Build/KTU84P) AppleWebkit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0)"
]

怎么获取这些头部？用火狐的插件user-agent switcher

之后的操作就是解析json

import random
import requests
import json
import time


first_url = 'https://m.douban.com/rexxar/api/v2/tv/26322642/interests?count=20&order_by=hot&start=0&ck=dNhr&for_mobile=1'
url = 'https://m.douban.com/rexxar/api/v2/tv/26322642/interests'
# 移动端头部信息
useragents = [
    "Mozilla/5.0 (iPhone; CPU iPhone OS 9_2 like Mac OS X) AppleWebKit/601.1 (KHTML, like Gecko) CriOS/47.0.2526.70 Mobile/13C71 Safari/601.1.46",
    "Mozilla/5.0 (Linux; U; Android 4.4.4; Nexus 5 Build/KTU84P) AppleWebkit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0)"
]


def visit_URL(i):
    print(">>>>>",i)
    # 请求头部
    headers = {
        'Host':'m.douban.com',
        'Upgrade-Insecure-Requests':'1',
        'User-Agent':random.choice(useragents)
    }
    params = {
        'count':'50',
        'order_by':'hot',
        'start':str(i),
        'for_mobile':'1',
        'ck':'dNhr'
    }
    res = requests.get(url=url,headers=headers,params=params)
    res_json = res.json()
    interests = res_json['interests']
    print(len(interests))
    for item in interests:
        with open('huge.txt','a',encoding='utf-8') as file:
            if item['user']:
                if item['user']['name']:
                    file.write('评论用户:'+item['user']['name']+'\n')
            else:
                file.write('评论用户:none\n')
            if item['create_time']:
                file.write('评论时间:'+item['create_time']+'\n')
            else:
                file.write('评论时间:none\n')
            if item['comment']:
                file.write('评论内容:'+item['comment']+'\n')
            else:
                file.write('评论内容:none\n')
            if item['rating']:
                if item['rating']['value']:
                    file.write('对电影的评分:'+str(item['rating']['value'])+'\n\n')
            else:
                file.write('对电影的评分:none\n')
    


if __name__ == '__main__':
    for i in range(0,66891,20):
        # time.sleep(2)
        visit_URL(i)

更多项目请关注https://github.com/ylfeng250/FengSpider