You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
pixiv/PixivSearch/dao/bangumi.py

139 lines
4.7 KiB

import _thread
import json
import math
import os
from concurrent import futures
from queue import Queue
import django
import requests
from bs4 import BeautifulSoup
from PixivSearch.settings import logger
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "PixivSearch.settings")
django.setup()
from PixivSearch.model.config import mediaInfo, stat
current_mediaInfo = None
isStop = None
def stop_():
global isStop
isStop = True
def save(params):
if isStop:
return
logger.info(params)
bangumi_id = params[0]
season_id = params[1]
media_id = params[2]
url = "https://www.bilibili.com/bangumi/media/md%d" % media_id
try:
req = requests.get(url, timeout=10)
except BaseException as e:
logger.error(repr(e))
save(media_id)
logger.info("request_url=%s,status_code=%d" % (url, req.status_code))
if req.status_code == 200:
tag = BeautifulSoup(req.text, 'lxml')
script = tag.select("script")[3].text
json_str = script[script.index("=") + 1:script.index("function") - 2]
json_obj = json.loads(json_str)
try:
if 'mediaInfo' in json_obj and 'stat' in json_obj['mediaInfo'] and 'chn_name' in json_obj['mediaInfo']:
stat_info = json_obj['mediaInfo']['stat']
print(stat_info)
mediaInfo(bangumi_id=bangumi_id, season_id=season_id, media_id=media_id,
chn_name=json_obj['mediaInfo']['chn_name']).save()
global current_mediaInfo
current_mediaInfo = mediaInfo.objects.get(pk=season_id)
stat(id=season_id, danmakus=int(stat_info['danmakus']), favorites=stat_info['favorites'],
views=stat_info['views']).save()
except BaseException as e:
logger.error(repr(e))
def get_():
global current_mediaInfo
return current_mediaInfo
page_size = 10
queue = Queue(page_size)
def listen():
while True:
ids = queue.get()
try:
executors = futures.ThreadPoolExecutor(page_size)
with executors as executor:
executor.map(save, ids)
logger.info('结束爬虫')
except BaseException as e:
logger.error(repr(e))
_thread.start_new_thread(listen, ())
def getIds():
seasonIdList = []
page = 1
pages = None
name = 'seasonListCallback'
global isStop
isStop = False
while isStop == False and (pages is None or page <= pages):
url = 'https://bangumi.bilibili.com/web_api/season/index_global?page=%d&page_size=%d' % (page, page_size)
logger.info(url)
try:
req = requests.get(url, timeout=10)
if req.status_code == 200:
json_obj = json.loads(req.text)
if 'result' in json_obj and 'list' in json_obj['result']:
bangumiList = json_obj['result']['list']
ids = []
for bangumi in bangumiList:
if isStop:
break
if 'season_id' in bangumi:
season_id = int(bangumi['season_id'])
if season_id in seasonIdList:
continue
url = 'https://bangumi.bilibili.com/jsonp/seasoninfo/%d.ver?callback=%s&jsonp=jsonp' % (
season_id, name)
logger.info(url)
req = requests.get(url, timeout=10)
if req.status_code == 200:
child_json_obj = json.loads(
req.text.replace('seasonListCallback(', '').replace(');', ''))
if 'result' in child_json_obj and 'bangumi_id' in child_json_obj['result']:
bangumi_id = int(child_json_obj['result']['bangumi_id'])
if 'media' in child_json_obj['result']:
media_id = int(child_json_obj['result']['media']['media_id'])
ids.append((bangumi_id, season_id, media_id))
seasonIdList.append(season_id)
if pages is None and 'count' in json_obj['result']:
pages = int(math.ceil(int(json_obj['result']['count']) / page_size))
page = page + 1
logger.info('获取id数量%d' % len(ids))
queue.put(ids)
except BaseException as e:
logger.error(repr(e))
continue
def A(e):
logger.info(e)
if __name__ == '__main__':
getIds()