豆瓣电影小实战

标题:豆瓣电影小实战

仅供参考：

# encoding=utf-8

import requests
from lxml import etree
# 1.将目标网站的页面抓取下来
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
                 'Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0',
    'Referer':'https://movie.douban.com/explore'
}
url = 'https://movie.douban.com/cinema/nowplaying/jinzhong/'
response = requests.get(url,headers=headers)
text = response.text
# response.text 返回的是一个经过解码后的字符串，是str(unicode类型)
# response.content 返回的是一个原生的字符串，就是从网页上抓取下来的，
#    没有经过处理的字符串，是bytes类型


# 2.将抓取下来的数据更具一定的规划进行提取
html = etree.HTML(text)
# // 获取网页当中所有的子孙元素
ul = html.xpath("//ul[@class='lists']")[0]
print(ul)
print(etree.tostring(ul,encoding='utf-8').decode('utf-8'))
lis = ul.xpath("./li")
movies = []
for li in lis:
    title = li.xpath("@data-title")[0]
    # 因为电影未上映，所以无 data-score
    #score = li.xpath("@data-score")[0]
    duration = li.xpath("@data-duration")[0]
    region = li.xpath("@data-region")[0]
    directer = li.xpath("@data-director")[0]
    actors = li.xpath("@data-actors")[0]
    thumbnail = li.xpath(".//img/@src")
    print(thumbnail)
    movie = {
        'title':title,
        'duration':duration,
        'region':region,
        'directer':directer,
        'actors':actors,
        'thumbnail':thumbnail

    }
    movies.append(movie)
print(movies)

import requests
from lxml import etree


#1.将目标网站的页面抓取下来
headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36",
    "Referer":"https://www.douban.com/"
}
url = "https://movie.douban.com/cinema/nowplaying/xinzhou/"
response = requests.get(url,headers=headers)
text = response.text
#print(response.text)
#response,.text返回的是一个经过解码的字符串，是str（unicode）类型
#response.content返回的是一个原生的字符串，是bytes类型
#2.将抓取下来的数据根据一定的规则进行提取
html = etree.HTML(text)
ul = html.xpath("//ul[@class='lists']")[1]
lis = ul.xpath("./li")
movies = []
for li in lis:
    title = li.xpath("@data-title")[0]
    score = li.xpath("@data-score")[0]
    duration =li.xpath("@data-duration")[0]
    region = li.xpath("@data-region")[0]
    director = li.xpath("@data-director")[0]
    actors = li.xpath("@data-actors")[0]
    #获取海报
    thumbnail = li.xpath(".//img/@src")
    movie = {
        "title":title,
        "score":score,
        "duration":duration,
        "region":region,
        "directors":director,
        "actors":actors,
        "thumbnail":thumbnail
    }
    movies.append(movie)

print(movies)