65 lines
1.8 KiB
Python
65 lines
1.8 KiB
Python
import requests
|
|
from bs4 import BeautifulSoup as bs
|
|
import json
|
|
|
|
url = 'https://exam.detr.top/exam-b/movies'
|
|
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/149.0.0.0 Safari/537.36 Edg/149.0.0.0',
|
|
'Referer':'https://exam.detr.top/exam-b/movies'}
|
|
req = requests.get(url, headers=headers)
|
|
req.encoding="utf-8"
|
|
|
|
data=[]
|
|
|
|
soup=bs(req.text,"html.parser")
|
|
# print(soup)
|
|
#id, title, director, year, rating, duration, genre, actors_count
|
|
|
|
item=soup.select("table tbody tr" )
|
|
movie_list=[]
|
|
|
|
for tr in item:
|
|
tds=tr.find_all("td")
|
|
tds=list(tds)
|
|
# print(tds)
|
|
if len(tds)<8:
|
|
continue
|
|
movie={
|
|
"id":tds[0].get_text(strip=True),
|
|
"title":tds[1].get_text(strip=True),
|
|
"director":tds[2].get_text(strip=True),
|
|
"year":tds[3].get_text(strip=True),
|
|
"rating":tds[4].get_text(strip=True),
|
|
"duration":tds[5].get_text(strip=True),
|
|
"genre":tds[6].get_text(strip=True),
|
|
"actors_count":tds[7].get_text(strip=True)
|
|
}
|
|
movie_list.append(movie)
|
|
print(movie_list)
|
|
|
|
|
|
with open('movie.json', 'w', encoding='utf-8') as f:
|
|
json.dump(movie_list, f, ensure_ascii=False, indent=2)
|
|
|
|
with open("move.html","w",encoding='utf-8') as f:
|
|
json.dump(movie_list, f, ensure_ascii=False, indent=2)
|
|
|
|
|
|
|
|
|
|
|
|
# for i in range(len(items)):
|
|
# rank=i+1
|
|
# title=items[i].find("span",class_="title").get_text()
|
|
# actors=items[i].find("div",class_="bd").get_text().strip()
|
|
# try:
|
|
# actors=actors.split("主演：")[1].split("\n")[0]
|
|
# except:
|
|
# actors="无"
|
|
# quote=items[i].find("p",class_="quote").get_text().strip()
|
|
|
|
# data.append({
|
|
# "rank":rank,
|
|
# "title":title,
|
|
# "actors":actors,
|
|
# "quote":quote
|
|
# }) |