1. import requests
    2. from bs4 import BeautifulSoup
    3. import csv
    5. def read_page(url, headers):
    6.     res = requests.get(url, headers=headers)
    7.     res.encoding = 'gb2312'
    8.     html = res.text
    9.     soup = BeautifulSoup(html, 'lxml')
    10.     zhuti = soup.find('div', class_='zhuti')
    11.     table = zhuti.find('table')
    12.     trs = table.find_all('tr')[1:]
    13.     lst = []
    14.     for tr in trs:
    15.         info = {}
    16.         tds = tr.find_all('td')
    17.         if tds:
    18.             name_td = tds[1]
    19.             movie_name = list(name_td.strings)[1]
    20.             piaofang_td = tds[-1]
    21.             piaofang = list(piaofang_td.strings)[0]
    22.             info['name'] = movie_name
    23.             info['piaofang'] = piaofang
    24.             lst.append(info)
    25.     return lst
    27. def write(lst):
    28.     with open('movies.csv', 'w', encoding='utf-8-sig', newline='') as f:
    29.         wt = csv.DictWriter(f, fieldnames=['name', 'piaofang'])
    30.         wt.writeheader()
    31.         wt.writerows(lst)
    33. url = 'http://www.piaofang.biz/'
    34. headers = {
    35. 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36'
    36. }
    37. lst = read_page(url, headers)
    38. write(lst)