张树袋
发表于 2020-7-24 15:57:18
朕想知道
weiyideid823
发表于 2020-7-24 16:02:04
朕想知道
教程表
发表于 2020-7-25 09:26:11
朕想知道
鲜格格
发表于 2020-7-25 23:36:57
朕想知道
lslslsls12
发表于 2020-7-27 16:29:05
1
syman0203
发表于 2020-7-27 16:50:47
小白,刚接触,要好好学习鸭
penut'
发表于 2020-7-27 18:54:55
1
jack_xy
发表于 2020-7-28 07:53:43
朕想知道
aa757818537
发表于 2020-7-28 14:09:35
1
能坚持几天
发表于 2020-7-28 16:44:13
朕想知道
hudayun
发表于 2020-7-28 20:18:10
支持小甲鱼
彻彻底底
发表于 2020-7-29 12:36:34
1
红蓝cp
发表于 2020-7-29 13:37:44
。。。
fengahao
发表于 2020-7-29 14:15:40
朕想知道
吾深知秋
发表于 2020-7-29 18:53:33
朕想知道
邱小冬
发表于 2020-7-30 17:04:23
{:5_90:}
温木zou
发表于 2020-7-31 11:48:50
giao
爱笑的皮卡媛
发表于 2020-8-2 16:44:28
lalala
aaron.yang
发表于 2020-8-2 18:59:24
联想知道
反清复明君
发表于 2020-8-3 11:37:14
import requests
import bs4
import re
import openpyxl
def open_url(url):
# 使用代理
# proxies = {"http": "127.0.0.1:1080", "https": "127.0.0.1:1080"}
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, proxies=proxies)
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(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(, ranks, messages])
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 save_to_excel(result):
wb = openpyxl.Workbook()
ws = wb.active
ws['A1'] = "电影名称"
ws['B1'] = "评分"
ws['C1'] = "资料"
for each in result:
ws.append(each)
wb.save("豆瓣TOP250电影.xlsx")
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("test.txt", "w", encoding="utf-8") as f:
for each in result:
f.write(each)
'''
save_to_excel(result)
if __name__ == "__main__":
main()