資源簡介
用Python爬蟲從豆瓣電影的首頁那一頁中,爬取那頁的電影名稱,上映時間,國家,豆瓣評分,主演,然后再講結果寫到*.txt文件中
代碼片段和文件信息
#?_*_?encoding:utf-8?_*_
import?requests
from?bs4?import?BeautifulSoup
import?json
import?time
import?random
def?get_movie_id(types):
????ids?=?[]
????contents?=?requests.get(
????????‘https://movie.douban.com/j/search_subjects?type=movie&tag={0}&sort=recommend&page_limit=50&page_start=0‘.format(
????????????types))
????subjiects?=?json.loads(contents.content.decode(“utf-8“))[“subjects“]
????for?subject?in?subjiects:
????????ids.append(subject[‘id‘])
????print(ids)
????return?ids
def?detail(_id):
????content?=?requests.get(‘https://movie.douban.com/j/subject_abstract?subject_id={0}‘.format(_id))
????subject?=?json.loads(content.content.decode(“u
評論
共有 條評論