def get_html(url):
response = urllib.request.urlopen(url)
return response.read()
def parse_main(html):
webpage = BeautifulSoup(html, features="html.parser")
table = webpage.find('table', id='itemList')
for a_tag in table.find_all('a', class_='all'):
parse_movie(get_html('https://www.somerandommovieswebsite.com' + a_tag['href']))
def parse_movie(html):
web_page = BeautifulSoup(html, features="html.parser")
info = web_page.find('h1', class_="moviename")
movies.append(info.text)
def main():
movies = []
parse_main(get_html('https://www.somerandommovieswebsite.com'))
print(movies)
if __name__ == '__main__':
main()
如何在嵌套在 parse_main 中的 parse_movie 中访问 movies 列表(在 main() 函数中定义)。由于“未解析的引用‘电影’”错误，无法将任何内容附加到列表。使用非本地没有帮助
请您参考如下方法:
我认为你不应该既不在这里使用全局变量也不将它作为参数传递:
def get_html(url):
response = urllib.request.urlopen(url)
return response.read()
def parse_main(html):
movies = []
webpage = BeautifulSoup(html, features="html.parser")
table = webpage.find('table', id='itemList')
for a_tag in table.find_all('a', class_='all'):
movies.append(
parse_movie(get_html('https://www.somerandommovieswebsite.com' + a_tag['href']))
)
return movies
def parse_movie(html):
web_page = BeautifulSoup(html, features="html.parser")
info = web_page.find('h1', class_="moviename")
return info.text
def main():
movies = parse_main(get_html('https://www.somerandommovieswebsite.com'))
print(movies)
if __name__ == '__main__':
main()
