from playwright.sync_api import sync_playwright
def get_data(url):
page.goto(url)
count = 0
title = ''
rating = ''
num = ''
quote = ''
movies = page.query_selector_all('.grid_view .item')
for movie in movies:
title_element = movie.query_selector('.hd a span.title')
rating_element = movie.query_selector('.star .rating_num')
num_element = movie.query_selector('.star span:nth-child(4)')
quote_element = movie.query_selector('.quote span.inq')
if title_element:
title = title_element.inner_text()
rating = rating_element.inner_text()
num = num_element.inner_text()
if quote_element:
quote = quote_element.inner_text()
print(f"名称: {title}, 评分: {rating}, 评价人数: {num}, 引言：{quote}")
count += 1
else:
print("Not found")
return count
with sync_playwright() as p:
browser = p.chromium.launch()
page = browser.new_page()
base_url = 'https://movie.douban.com/top250'
sum = 0
for i in range(0,10):
url = r'https://movie.douban.com/top250?start='+str(i*25)+'&filter='
count = get_data(url)
sum += count
print("总记录数：", sum)
发表于 2025-3-27 16:06
