爬取豆瓣top250的电影排行
我们在在观看一部电影之前，通常会在网上查看评分，而基本上这些评分都是来自于豆瓣，今天我就教大家如何用python爬取豆瓣top250的排名，代码如下：import requests
import bs4
import re
def open_url(url):
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
res = requests.get(url, headers=headers)
return res
def find_movies(res):
soup = bs4.BeautifulSoup(res.text, 'html.parser')
# 电影名
movies = []
targets = soup.find_all("div", class_="hd")
for each in targets:
movies.append(each.a.span.text)
# 评分
ranks = []
targets = soup.find_all("span", class_="rating_num")
for each in targets:
ranks.append(' 评分：%s ' % each.text)
# 资料
messages = []
targets = soup.find_all("div", class_="bd")
for each in targets:
try:
messages.append(each.p.text.split('\n').strip() + each.p.text.split('\n').strip())
except:
continue
result = []
length = len(movies)
for i in range(length):
result.append(movies + ranks + messages + '\n')
return result
# 找出一共有多少个页面
def find_depth(res):
soup = bs4.BeautifulSoup(res.text, 'html.parser')
depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
return int(depth)
def main():
host = "https://movie.douban.com/top250"
res = open_url(host)
depth = find_depth(res)
result = []
for i in range(depth):
url = host + '/?start=' + str(25 * i)
res = open_url(url)
result.extend(find_movies(res))
with open("豆瓣TOP250电影.txt", "w", encoding="utf-8") as f:
for each in result:
f.write(each)
if __name__ == "__main__":
main()
谢谢楼主分享，学习了 测试过了，可以获取到，感谢楼主分享{:1_921:} 谢谢楼主分享，学习了 实测 有用 辛苦楼主了{:17_1060:} 谢谢分享 谢谢分享啊 谢谢分享 感谢分享 辛苦楼主，之后试试看