【Python爬虫】120行代码爬取豆瓣电影，附源码( 二 )_学习爬虫

urls = re.findall(pattern1 response.text)
directors = [
# 导演
names = [
# 电影名
stars = [
# 主演
countrys = [
# 电影的出产地
languages = [
# 电影语言
headers_urls = {
'Host':'movie.douban.com'
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML like Gecko) Chrome/73.0.3683.103 Safari/537.36'

# <span property=\"v:itemreviewed\">肖申克的救赎 The Shawshank Redemption</span>
# <a href=https://mparticle.uc.cn/"/celebrity/1047973/\" rel=\"v:directedBy\">弗兰克·德拉邦特</a>
# <a href=https://mparticle.uc.cn/"/celebrity/1054521/\" rel=\"v:starring\">蒂姆·罗宾斯</a>
def base_urls(base_url):
urls = [

# 这里我们只能前两页做测试，所以range只设置到了50
# for i in range(0 275 25):
# true_url = base_url.format(i)
# print(true_url)
for i in range(0 50 25):
true_url = base_url.format(i)
print(true_url)
response = requests.get(true_url headers=headers)
if response.status_code == 200: