学习python第五天

豆瓣TOP250爬虫

# 导入
import requests
from lxml import etree
def spider_douban_top250():
    movie_list_info = []
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"}
    for i in range(0, 250, 25):
        url = 'https://movie.douban.com/top250?start={}&filter='.format(i)

        # 获取bytes类型响应
        data = requests.get(url, headers=headers).content
        html = etree.HTML(data)



        ol_list = html.xpath('//div[@id="content"]//div[@class="article"]/ol/li')

        for movie in ol_list:
            # 影片序号
            serial_number = movie.xpath('./div[@class="item"]/div[@class="pic"]/em/text()')
            if len(serial_number) == 0:
                serial_number = ''
            else:
                serial_number = serial_number[0]
            # print(serial_number)
            # 电影的名字
            movie_name = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="hd"]/a/span[1]/text()')[0]
            # print(movie_name)
            # 电影的介绍
            movie_introduce = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[1]/text()')[0].strip()
            # print(movie_introduce)
            # 电影的星级
            star = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[2]/text()')[0]
            # print(star)
            # 电影的评价
            evalute = movie.xpath(
                './div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[4]/text()')
            evalute = evalute[0].replace('人评价', '')
            # print(evalute)
            # 电影的描述
            describe = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[@class="quote"]/span[1]/text()')
            # print(describe)
            # 电影封面的地址
            movie_img_url = movie.xpath('./div[@class="item"]/div[@class="pic"]/a/img/@src')[0]
            # print(movie_img_url)

            movie_list_info.append({
                'serial_number': serial_number,
                'movie_name': movie_name,
                'movie_introduce': movie_introduce,
                'star': star,
                'evalute': evalute,
                'describe': describe,
                'movie_img_url': movie_img_url
            })
    for movie in movie_list_info:
        print(movie)

        # 下载图片
    for movie in movie_list_info:
        url = movie['movie_img_url']
        resp = requests.get(url)
        if resp.status_code == 200:
            img_name = '0000000{}.jpg'.format(movie['serial_number'])
            with open('./imgs/{}'.format(img_name), 'wb') as f:
                f.write(resp.content)

spider_douban_top250()
  1. 需要用到lxml库中的etree,导入etree
from lxml import etree
  1. 获取bytes请求
data = requests.get(url, headers=headers).content
        html = etree.HTML(data)
  1. 依次遍历，取得所需要的数据

        for movie in ol_list:
            # 影片序号
            serial_number = movie.xpath('./div[@class="item"]/div[@class="pic"]/em/text()')
            if len(serial_number) == 0:
                serial_number = ''
            else:
                serial_number = serial_number[0]
            # print(serial_number)
            # 电影的名字
            movie_name = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="hd"]/a/span[1]/text()')[0]
            # print(movie_name)
            # 电影的介绍
            movie_introduce = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[1]/text()')[0].strip()
            # print(movie_introduce)
            # 电影的星级
            star = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[2]/text()')[0]
            # print(star)
            # 电影的评价
            evalute = movie.xpath(
                './div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[4]/text()')
            evalute = evalute[0].replace('人评价', '')
            # print(evalute)
            # 电影的描述
            describe = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[@class="quote"]/span[1]/text()')
            # print(describe)
            # 电影封面的地址
            movie_img_url = movie.xpath('./div[@class="item"]/div[@class="pic"]/a/img/@src')[0]
            # print(movie_img_url)

电影封面地址用于下载图片

     # 下载图片
    for movie in movie_list_info:
        url = movie['movie_img_url']
        resp = requests.get(url)
        if resp.status_code == 200:
            img_name = '0000000{}.jpg'.format(movie['serial_number'])
            with open('./imgs/{}'.format(img_name), 'wb') as f:
                f.write(resp.content)

.eg 阳光电影最新电影爬虫，代码未写完，正在进行中......仅供参考！！！

注意：

  1. 所需要访问的网页量数据庞大，代码中还存在许多的错误需要纠正
    2.代码在短时间内会频繁访问该网站，会出现主机无响应等错误，所以设置代理
def get_ip_list(url, headers):
    web_data = requests.get(url, headers=headers)
    soup = BeautifulSoup(web_data.text, 'lxml')
    ips = soup.find_all('tr')
    ip_list = []
    for i in range(1, len(ips)):
        ip_info = ips[i]
        tds = ip_info.find_all('td')
        ip_list.append(tds[1].text + ':' + tds[2].text)
    return ip_list

def get_random_ip(ip_list):
    proxy_list = []
    for ip in ip_list:
        proxy_list.append('http://' + ip)
    proxy_ip = random.choice(proxy_list)
    proxies = {'http': proxy_ip}
    return proxies

url = 'http://www.xicidaili.com/nn/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
}
ip_list = get_ip_list(url, headers=headers)
proxies = get_random_ip(ip_list)

# 导入
import requests
import random
from bs4 import BeautifulSoup
# from lxml import etree
from lxml import html
from lxml import etree
def get_ip_list(url, headers):
    web_data = requests.get(url, headers=headers)
    soup = BeautifulSoup(web_data.text, 'lxml')
    ips = soup.find_all('tr')
    ip_list = []
    for i in range(1, len(ips)):
        ip_info = ips[i]
        tds = ip_info.find_all('td')
        ip_list.append(tds[1].text + ':' + tds[2].text)
    return ip_list

def get_random_ip(ip_list):
    proxy_list = []
    for ip in ip_list:
        proxy_list.append('http://' + ip)
    proxy_ip = random.choice(proxy_list)
    proxies = {'http': proxy_ip}
    return proxies
def spider_douban_top250():
    img = 1
    movie_list_info = []
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 8.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"}
    for i in range(1, 200):
        url = 'https://www.ygdy8.net/html/gndy/dyzz/list_23_{}.html'.format(i)

        # 获取bytes类型响应
        data = requests.get(url, headers=headers,proxies=proxies)
        data.encoding = 'GBK'
        data = data.text
        selector = html.fromstring(data)
        # html = etree.HTML(data)



        ol_list = selector.xpath('//div[@class="co_content8"]/ul//table')
        print(len(ol_list))
        # print(ol_list)

        n = 0
        for movie in ol_list:
            # # 电影名称
            # name = movie.xpath('//a[@class="ulink"]/text()')[n]
            # 电影详细信息连接
            link = movie.xpath('//a[@class="ulink"]/@href')[n]
            link = 'https://www.ygdy8.net'+link
            # print(link)
            detail = requests.get(link,headers=headers,proxies=proxies).content
            depage = etree.HTML(detail)
            # 电影名称
            name = depage.xpath('//p/text()')
            if name == '':
                continue
            else:
                name = name[5].strip()
                if name == '':
                    name = depage.xpath('//p/text()')[6][6:].strip()
                if name == '':
                    name = depage.xpath('//text()')[3]

            print(img,name)
            # print(depage.xpath('//p/text()'))

            # 电影国家

            # country = depage.xpath('//p/text()')[10].strip()[6:]
            # print(country)

            # 电影年代
            # year = depage.xpath('//p/text()')[9].strip()[6:]
            # print(year)

            # 类别
            # type = depage.xpath('//p/text()')[11].strip()[6:]
            # print(type)

            # 语言
            # languag = depage.xpath('//p/text()')[12].strip()[6:]
            # print(languag)

            # 字幕
            # word = depage.xpath('//p/text()')[13].strip()
            # print(word)
            #电影封面链接
            src = depage.xpath('//img/@src')[1]
            # print(src)
            resp = requests.get(src)
            if resp.status_code == 200:
                with open('./ygdyIMG/{}.jpg'.format(img),'wb') as f:
                    f.write(resp.content)
            else:
                continue
            # print(link)

            # print(name)

             # 影片序号
        #     serial_number = movie.xpath('./div[@class="item"]/div[@class="pic"]/em/text()')
        #     if len(serial_number) == 0:
        #         serial_number = ''
        #     else:
        #         serial_number = serial_number[0]
        #     # print(serial_number)
            # 电影的名字
            # print(movie)
            # movie_name = movie.xpath('//div[@class="co_content8"]/ul//table/tbody[1]/tr[1]')
            # print(movie_name)
        #     # 电影的介绍
        #     movie_introduce = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[1]/text()')[0].strip()
        #     # print(movie_introduce)
        #     # 电影的星级
        #     star = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[2]/text()')[0]
        #     # print(star)
        #     # 电影的评价
        #     evalute = movie.xpath(
        #         './div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[4]/text()')
        #     evalute = evalute[0].replace('人评价', '')
        #     # print(evalute)
        #     # 电影的描述
        #     describe = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[@class="quote"]/span[1]/text()')
        #     # print(describe)
        #     # 电影封面的地址
        #     movie_img_url = movie.xpath('./div[@class="item"]/div[@class="pic"]/a/img/@src')[0]
        #     # print(movie_img_url)
            n += 1
            img += 1
            # movie_list_info.append({
            #     'serial_number': serial_number,
            #     'movie_name': movie_name,
            #     'movie_introduce': movie_introduce,
            #     'star': star,
            #     'evalute': evalute,
            #     'describe': describe,
            #     # 'movie_img_url': movie_img_url
            # })
    # for movie in movie_list_info:
    #     print(movie)
    #
    #     # 下载图片
    # for movie in movie_list_info:
    #     url = movie['movie_img_url']
    #     resp = requests.get(url)
    #     if resp.status_code == 200:
    #         img_name = '0000000{}.jpg'.format(movie['serial_number'])
    #         with open('./imgs/{}'.format(img_name), 'wb') as f:
    #             f.write(resp.content)


url = 'http://www.xicidaili.com/nn/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
}
ip_list = get_ip_list(url, headers=headers)
proxies = get_random_ip(ip_list)
spider_douban_top250()

所用的知识均为前面几篇文章所讲。

程序会访问4976个网页，会比较慢，并且网页结构并不是完全相同，需要在代码上做修改

最后编辑于 ：
©著作权归作者所有,转载或内容合作请联系作者
【社区内容提示】社区部分内容疑似由AI辅助生成，浏览时请结合常识与多方信息审慎甄别。
平台声明：文章内容（如有图片或视频亦包括在内）由作者上传并发布，文章内容仅代表作者本人观点，简书系信息发布平台，仅提供信息存储服务。

友情链接更多精彩内容