Python爬取豆瓣正在上映的电影信息

环境

python3.6 + requests+lxml

Lxml资料

分析

网址：https://movie.douban.com/cinema/nowplaying/chengdu/

F12分析网页，通过lxml解析requests获取的到页面信息，筛选出自己电影相关信息。

源码

importrequests

fromlxmlimportetree

importos

defparse1(url):

response = requests.get(url).content

response = etree.HTML(response)

datas = response.xpath('//div[@id="nowplaying"]/div[2]/ul/li')

fordataindatas:

all_attrib = data.attrib

name = all_attrib['data-title']

score = all_attrib['data-score']

director = all_attrib['data-director']

actors = all_attrib['data-actors']

duration = all_attrib['data-duration']

poster_url = data.xpath('ul/li[@class="poster"]/a/img/@src')[]

info_url = data.xpath('ul/li[@class="poster"]/a/@href')[]

info = parse2(info_url)

if notos.path.exists('movies/'+name):

os.makedirs('movies/'+name)

withopen('movies/'+name+'/'+name+'.txt','w')asft:

all_info ='电影:'+name +'\n'+'评分:'+score+'\n'+'时长:'+duration+'\n'\

'导演:'+director+'\n'+'主演:'+actors+'\n'+'剧情:'+info+'\n'

ft.write(all_info.replace('\u22ef','...'))

download(name,poster_url)

defparse2(url):

response = requests.get(url).content

response = etree.HTML(response)

datas = response.xpath('//div[@class="related-info"]')

info =''

fordataindatas:

info = data.xpath('div/span/text()')[].strip()

returninfo

defdownload(name,url):

content = requests.get(url).content

withopen('movies/'+name+'/'+name+'.jpg','wb')asfp:

fp.write(content)

if__name__ =='__main__':

nowplaying_url ='https://movie.douban.com/cinema/nowplaying/chengdu/'

parse1(nowplaying_url)