初始python 之 爬虫：爬取豆瓣电影最热评论

Posted 2022-04-29 simple-li

不废话，直接上干货：

#!/user/bin env python
# author:Simple-Sir
# time:2019/7/17 22:08
# 获取豆瓣网正在上映电影最热评论
import requests
from lxml import etree

# 伪装浏览器
headers =
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/63.0.3239.132 Safari/537.36‘,
    ‘Referer‘:‘https://movie.douban.com/‘

# 获取首页网页信息并解析
url = ‘https://movie.douban.com/cinema/nowplaying/chengdu/‘

def getUrlText(url):
    respons = requests.get(url,headers=headers)  # 获取网页信息
    urlText = respons.text
    html = etree.HTML(urlText)  # 使用lxml解析网页
    return html

# 提取电影名称及详情地址链接列表
def getWallUrl(url):
    hrefUrl = getUrlText(url)
    ul = hrefUrl.xpath(‘//ul[@class="lists"]‘)[0]  # 获取ul标签
    liList = ul.xpath(‘./li‘)  # # 获取li标签列表
    liHrefs = []
    for li in liList:
        liHref = li.xpath(‘.//@href‘)[0]
        name = li.xpath(‘@data-title‘)[0]
        msg = 
            name:liHref
        
        liHrefs.append(msg)
    return liHrefs

# 解析电影详情地址
def downPL(url):
    moveUrl = getWallUrl(url)
    n=0
    for murl in moveUrl:
        n+=1
        for d in murl:
            plHtml = getUrlText(murl[d])
            plTextFull = plHtml.xpath(‘//div[@id="hot-comments"]//span[@class="hide-item full"]//text()‘)
            plTextShort = plHtml.xpath(‘//div[@id="hot-comments"]//span[@class="short"]//text()‘)
            if(len(plTextFull)==0 and len(plTextShort)>0):
                print(‘正在写入《》的评论。‘.format(d))
                with open(‘豆瓣评论.txt‘,‘a+‘,encoding=‘utf-8‘) as fp:
                    fp.write(‘、《》的最热评论是：\\n\\n\\n‘.format(n,d,plTextShort[0]))
            elif(len(plTextFull)>0):
                print(‘正在写入《》的评论。‘.format(d))
                with open(‘豆瓣评论.txt‘,‘a+‘,encoding=‘utf-8‘) as fp:
                    fp.write(‘、《》的最热评论是：\\n\\n\\n‘.format(n,d,plTextShort[0]))
            else:
                print(‘正在写入《》的评论。‘.format(d))
                with open(‘豆瓣评论.txt‘,‘a+‘,encoding=‘utf-8‘) as fp:
                    fp.write(‘、《》暂无评论！\\n\\n‘.format(n,d))
    return print(‘部电影的所有评论已全部写入“豆瓣评论.txt”，请查看。‘.format(n))

if __name__ == ‘__main__‘:
    downPL(url)

 

执行效果：

 

 文件详情：