import requests
from bs4 import BeautifulSoup
def getHTML(url):
html = requests.get(url)
return html.text
def getInfo(list, qlist):
cnt = 0
flag = 0
for i in range(10):
turl = 'https://movie.douban.com/top250?start=' + str(i*25)
html = getHTML(turl)
soup = BeautifulSoup(html, 'html.parser')
links = soup.find_all('div', class_='hd')
for link in links:
cnt = cnt + 1
movie = link.a.span.text.strip()
list.append([cnt, movie])
quotes = soup.find_all('p', class_='quote')
for quote in quotes:
flag = flag + 1
movie_quote = quote.span.text.strip()
qlist.append(movie_quote)
def printInfo(list,qlist):
module = "{0:^5}\t{1:{3}^20}\t{2:{3}<30}"
print(module.format("排名", "电影名称", "一句话概括", chr(12288)))
for i in range(1, 250):
l_ = list[i]
q_ = qlist[i]
print(module.format(l_[0], l_[1], q_, chr(12288)))
def main():
list = []
qlist = []
getInfo(list, qlist)
printInfo(list, qlist)
if __name__ == '__main__':
main()
爬取豆瓣top250的电影和电影概括
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
- 文/潘晓璐 我一进店门，熙熙楼的掌柜王于贵愁眉苦脸地迎上来，“玉大人，你说我怎么就摊上这事。” “怎么了？”我有些...
- 文/花漫 我一把揭开白布。 她就那样静静地躺着，像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上，一...
- 文/苍兰香墨 我猛地睁开眼，长吁一口气：“原来是场噩梦啊……” “哼！你这毒妇竟也来了？” 一声冷哼从身侧响起，我...
