一个豆瓣电影Top250爬虫

一个爬虫

这是我第一次接触爬虫，写的第一个爬虫实例。

https://movie.douban.com/top250

模块

import requests #用于发送请求
import re #使用正则表达式，用于匹配处理文本
import os #用于创建文件夹
from lxml import etree #这里我使用了Xpath表达式用于数据解析，我觉得这个模块比BeautifulSoup好用，强烈推荐
from fake_useragent import UserAgent #反爬虫，随机获取浏览器 UA 信息

代码

import requests
import re
import os
from lxml import etree
from fake_useragent import UserAgent


class doubanSpider(object):
    def __init__(self):
        if not os.path.exists('db/douban'):
            os.makedirs('db/douban')
        else:
            pass
        self.f = open('./db/douban/douban.txt', 'a', encoding='utf-8')

    def start(self):
        for i in range(46):
            headers = {
                'User-Agent': UserAgent().random
            }
            url = 'https://movie.douban.com/top250?start=' + str(i * 25)
            r = requests.get(url, headers=headers)
            html = etree.HTML(r.text)
            li_list = html.xpath('//*[@id="content"]/div/div[1]/ol/li')
            movies = []
            for each in li_list:
                movie = {}
                order = each.xpath('.//div/div[1]/em/text()')[0]
                movie['id'] = order
                cover = each.xpath('.//div/div[1]/a/img/@src')[0]
                movie['cover'] = cover
                name = each.xpath('.//div/div[2]/div[1]/a/span/text()')
                flag = ''
                for mo in name:
                    flag += mo
                movie['name'] = flag
                info = each.xpath('.//div/div[2]/div[2]/p[1]/text()[1]')[0].strip()
                info = info.replace("\n", "")
                info = info.replace("\xa0", "")
                director = re.findall(r'[导演:].+[主演:]', info)[0]
                director = director[4:len(director) - 3]
                movie['director'] = director
                try:
                    role = re.findall(r'主.+', info)[0]
                    role = role[4:]
                except IndexError:
                    role = ''
                movie['role'] = role
                plot = each.xpath('.//div/div[2]/div[2]/p[1]/text()[2]')[0].strip()
                plot = plot.replace("\xa0", "")
                movie['plot'] = plot
                star = each.xpath('.//div/div[2]/div[2]/div/span[2]/text()')[0]
                movie['star'] = star
                try:
                    comment = each.xpath('.//div/div[2]/div[2]/p[2]/span/text()')[0]
                except IndexError:
                    comment = ''
                movie['comment'] = comment
                movies.append(movie)
                self.f.write(str(movie)+'\n')
                print(movie)

    def run(self):
        self.start()
        self.f.close()


if __name__ == '__main__':
    spider = doubanSpider()
    spider.run()

标签：xpath,movie,爬虫,豆瓣,text,each,import,div,Top250
来源： https://www.cnblogs.com/ouhouyi/p/16410564.html