|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
本人是用mac运行的,代码如下
import requests
import bs4
import re
def open_url(url):
# 使用代理
# proxies = {"http": "127.0.0.1:1080", "https": "127.0.0.1:1080"}
headers = {
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36'}
# res = requests.get(url, headers=headers, proxies=proxies)
res = requests.get(url, headers=headers)
return res
def find_movies(res):
soup = bs4.BeautifulSoup(res.text, 'html.parser')
# 电影名
movies = []
targets = soup.find_all("div", class_="hd")
for each in targets:
movies.append(each.a.span.text)
# 评分
ranks = []
targets = soup.find_all("span", class_="rating_num")
for each in targets:
ranks.append(' 评分:%s ' % each.text)
# 资料
messages = []
targets = soup.find_all("div", class_="bd")
for each in targets:
try:
messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
except:
continue
result = []
length = len(movies)
for i in range(length):
result.append(movies[i] + ranks[i] + messages[i] + '\n')
return result
# 找出一共有多少个页面
def find_depth(res):
soup = bs4.BeautifulSoup(res.text, 'html.parser')
depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
return int(depth)
def main():
host = "https://movie.douban.com/top250"
res = open_url(host)
depth = find_depth(res)
result = []
for i in range(depth):
url = host + '/?start=' + str(25 * i)
res = open_url(url)
result.extend(find_movies(res))
with open("豆瓣TOP250电影.txt", "w", encoding="utf-8") as f:
for each in result:
f.write(each)
if __name__ == "__main__":
main()
输出的结果是Process finished with exit code 0,但是我找不到“豆瓣TOP250电影.txt”。有没有大佬知道原因
|
|