Python获取时光网电影数据的实例代码
# Encoding: utf-8
# Author: furongbing
# Date: 2021-11-19 20:54
# Project name: FrbPythonFiles
# IDE: PyCharm
# File name: Mtime
import requests
import pandas as pd
from threading import Thread
import time
import json
# 模块说明:
"""
从时光网上按年代获取指定年份电影的数据
"""
# 更新日志:
"""
1、2021-11-19:
a、完成初版
"""
# 待修改:
"""
"""
# 请求头数据
headers = {"Accept": "application/json, text/plain, */*",
"Accept-Encoding": "gzip, deflate",
'Accept-Language': 'zh-CN,zh;q=0.9',
'Connection': 'keep-alive',
'Content-Type': 'application/x-www-form-urlencoded',
'Cookie': '_tt_=FB8A3FAD4704D42543B7EC121C2565AA; __utma=196937584.1082595229.1637326918.1637326918.1637326918.1; __utmz=196937584.1637326918.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); Hm_lvt_07aa95427da600fc217b1133c1e84e5b=1637241042,1637326637,1637374129; Hm_lpvt_07aa95427da600fc217b1133c1e84e5b=1637374170',
'Host': 'front-gateway.mtime.com',
'Origin': 'http://film.mtime.com',
'Referer': 'http://film.mtime.com/',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36'
}
pagesize = 20 # todo 获取的每页数据条数,一般建议成默认的20就可以了,设置的太大,每页包含的数据量就大,某一条电影数据出错会导致其它数据也被抛弃。
data = []
error = []
def get_data(p_year=1987): # 按照年份获取当年度所有的电影数据
url = 'http://front-gateway.mtime.com/mtime-search/search/unionSearch2' # 请求的url
params = {'year': p_year, 'pageSize': pagesize, 'pageIndex': 1, 'searchType': 0} # 请求的表单数据
# 获取当年度所有的电影的数量,继而计算要获取多少页
try:
r = requests.get(url=url, params=params, headers=headers, timeout=10)
r.encoding = r.apparent_encoding
all_data = json.loads(r.text)
moviesCount = all_data['data']['moviesCount']
pages = round(moviesCount / pagesize)
except Exception:
moviesCount = 1000
pages = round(moviesCount / pagesize)
# 定义变量
来源 = '时光网'
年代 = p_year
ID, 中文名, 英文名, 类型, 形式, 海报url, 评分, 导演, 主演, 详情, 可播放, 国家地区, 上映日期, 片长, 票房, 观看日期 = [''] * 16
for page in range(pages): # todo 一共要获取多少页
if page % 10 == 0: # 每10页输出一次进度
print(f'已完成 {100 * page / pages:.2f}%')
pageindex = page + 1
params = {'year': p_year, 'pageSize': pagesize, 'pageIndex': pageindex, 'searchType': 0} # 请求的表单数据
try: # 获取指定页的电影数据
r = requests.get(url=url, params=params, headers=headers, timeout=10)
r.encoding = r.apparent_encoding
all_data = json.loads(r.text)
movies = all_data['data']['movies']
# 获取电影具体信息
for movie in movies:
ID = movie['movieId']
中文名 = movie['name']
英文名 = movie['nameEn']
类型 = movie['movieType']
形式 = movie['movieContentType']
海报url = movie['img']
其它译名 = movie['titleOthersCn']
评分 = movie['rating']
导演 = movie['directors']
主演 = movie['actors']
详情 = movie['href']
可播放 = movie['canPlay']
国家地区 = movie['locationName']
上映日期 = movie['realTime']
片长 = movie['length']
info = [来源, 年代, ID, 中文名, 英文名, 类型, 形式, 海报url, 其它译名, 评分, 导演, 主演, 详情, 可播放, 国家地区, 上映日期, 片长, 票房, 观看日期]
data.append(info)
except Exception as err:
er_year, er_pagesize, er_pageindex, er_msg = p_year, pagesize, pageindex, err
error.append([er_year, er_pagesize, er_pageindex, er_msg])
print(f"出错啦,出错年份:{p_year},pagesize:{pagesize},page:{pageindex},出错原因:{er_msg}")
continue
if __name__ == '__main__':
begin = time.perf_counter()
threads = []
for year in range(2020, 2021): # todo 此处可以自定义要获取的年份
t = Thread(target=get_data, args=(year,))
threads.append(t)
t.start()
for t in threads:
t.join()
with open('error.txt', 'w', encoding='utf-8') as f:
f.write(str(error))
data.insert(0, ['来源', '年代', 'ID', '中文名', '英文名', '类型', '形式', '海报url', '其它译名', '评分', '导演', '主演', '详情', '可播放', '国家地区', '上映日期', '片长', '票房', '观看日期'])
df = pd.DataFrame(data)
df.to_excel(excel_writer=r'film.xlsx', sheet_name='sheet1', index=None, header=False) # todo film.xlsx为最后保存的文件名
end = time.perf_counter()
runtime = end - begin
print(f'运行时长:{runtime:.3f}秒。')