acwing爬虫
作者:
划船全靠浪
,
2023-06-01 20:42:36
,
所有人可见
,
阅读 318
acwing个人做题数据获取爬虫代码
关于cookie怎么获取自行百度, 懂F12的都会
import re
import requests
from bs4 import BeautifulSoup
base_url = 'https://www.acwing.com/problem/'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko)'
' Chrome/68.0.3440.84 Safari/537.36',
'Referer': base_url,
'Cookie': ''
}
k = requests.session()
k.headers = headers
k.headers['Cookie'] = input('请输入你的acwing的cookie:')
acwing_rating = {
'简单': 0,
'中等': 0,
'困难': 0
}
print('acwing 搜索开始')
for page in range(1, 10000):
url = base_url + str(page) + '/'
dem = k.get(url)
dome = BeautifulSoup(dem.text, 'html.parser')
if len(dome.tbody.contents) <= 1:
break
for i in dome.tbody.contents:
try:
if not len(re.findall('通过', str(i.contents[1]))):
continue
print(i.contents[5].a.string[:-20].strip())
print('题目编号: ', i.contents[3].span.string)
print('困难程度: ', i.contents[9].string)
print('')
acwing_rating[i.contents[9].string] += 1
except:
pass
print('acwing搜索结束')
print(acwing_rating)
print()
前来点赞