环境：Pycharm 2019.3 + Anaconda3 2020.02

代码

import urllib.request
import time
import re
import os
​
​
def save(page_id, title, en_title, college, info, source):
    with open('2017210213.txt', 'a') as f1:
        try:
            info = info.encode('gbk').decode('gbk')
        except UnicodeEncodeError:
            info = 'gbk无法编码'
        key = 'id:{}\ntitle:{}\nen_title:{}\ncollege:{}\ninfo:{}\nsource:{}\n\n' \
            .format(page_id, title, en_title, college, info, source)
        key_gbk = key.encode('gbk').decode('gbk')
        f1.write(key_gbk)
        print(page_id, 'save')
​
​
def get_page(page_id):
    opener = urllib.request.build_opener()
    opener.add_headers = [
        ("accept-encoding", "identity;q=1,*;q=0"),
        ("accept-language", "zh-CN,zh;q=0.9"),
        ('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36')
    ]
    urllib.request.install_opener(opener)
    url = 'https://win.bupt.edu.cn/program.do?id='+str(page_id)
    response = urllib.request.urlopen(url)
    time.sleep(3)
    text = response.read().decode('utf-8')
    print(page_id, 'got')
    return text
​
​
def find(page_id, text):
    reg = r'<h2 style="display:inline">(.*?)</h2>.*?' \
          r'<h3 style="display:inline;">&nbsp;(.*?)</h3>.*?' \
          r'<div style="font-size:17px;line-height:25px;">.*?' \
          r'<div style="margin-top:-7px;overflow: hidden;white-space: nowrap;text-overflow: ellipsis;">(.*?)</div>.*?' \
          r'<div style="font-size:17px;line-height:25px;">(.*?)</div>'
    pattern = re.compile(reg, re.S)
    key = pattern.findall(text)
    pattern_s = re.compile(r'var eval_score.*?name":"(.*?)\\u8bad\\u7ec3\\u8ba1\\u5212', re.S)
    s = pattern_s.findall(text)
    if key:
        title = key[0][0].strip()
        en_title = key[0][1].strip()
        college = key[0][2].strip()
        info = key[0][3].replace('\n', ' ').replace('\r', ' ').strip()
        source = s[0].strip().encode('utf-8').decode('unicode_escape')
        save(page_id, title, en_title, college, info, source)
    else:
        print(page_id, 'not exist')
        return page_id
​
​
if os.path.exists('2017210213.txt'):
    with open('2017210213.txt', 'r')as f:
        lines = f.readlines()
        last = lines[-6]
        last_id = re.findall(r'\d+', last)[0]
        print('begin from', last_id)
else:
    last_id = 1200
​
for i in range(int(last_id)+1, 1414):
    page = get_page(i)
    find(i, page)

后记

这个作业因为在写入txt文件时，多了一个换行符被扣了10分，black同学告诉我群里说过，我太阳痿了。