def check(self, list_data, offset, cnt):
"""
:param list_data: 请求返回的结果
:param offset:
:return: 带着本次请求的参数和结果一起过安检
请求失败导致安检不通过 安检提醒人重新操作手机 操作完之后再次发起请求
不排除还是会失败 继续调用自己
"""
if list_data != 'req_data_error':
stop_and_start.check({'crawler': '历史文章列表', 'msg': 'success'})
else:
stop_and_start.check({
'crawler': '历史文章列表',
'msg': 'req_data_error'
})
self.wx_req_data_list = rd.tidy()
while len(self.wx_req_data_list) == 0:
self.wx_req_data_list = rd.tidy()
from utils.front import notification
notification('没有发现参数', '参数错误', _type='error')
time.sleep(3)
list_data = Crawler(offset, self.wx_req_data_list[0]).run()
self.check(list_data, offset, cnt)
return list_data
def __init__(self):
self.wx_req_data_list = rd.tidy()
self.nickname = self.wx_req_data_list[0]['nickname']
self.every_delay = 3.0
self.wx_num = len(self.wx_req_data_list)
self.delay = round(self.every_delay / self.wx_num, 3)
self.articles = []
self.col_data = CollectionOperation(self.nickname)
self.pre_crawl_time = time.time()
def check(self, reading_data, item):
"""
:return: 带着本次请求的参数和结果一起过安检
请求失败导致安检不通过 安检提醒人重新操作手机 操作完之后再次发起请求
不排除还是会失败 继续调用自己 反正想办法让其获得成功的请求 最后返回成功的请求
"""
if reading_data != 'req_data_error':
stop_and_start.check({'crawler': '阅读数据', 'msg': 'success'})
else:
stop_and_start.check({'crawler': '阅读数据', 'msg': 'req_data_error'})
self.wx_req_data_list = rd.tidy()
while len(self.wx_req_data_list) == 0:
self.wx_req_data_list = rd.tidy()
from utils.front import notification
notification('没有发现参数', '参数错误', _type='error')
time.sleep(3)
reading_data = Crawler(item[1], item[2],
self.wx_req_data_list[0]).run()
self.check(reading_data, item)
return reading_data
def __init__(self):
# 从数据源获取的请求参数
self.wx_req_data_list = rd.tidy()
# 微信昵称
self.nickname = self.wx_req_data_list[0]['nickname']
# 同一个微信账号两次请求之间的时间间隔
self.every_delay = 3.0
# 参加采集微信的数量
self.wx_num = len(self.wx_req_data_list)
# 多个微信账号的情况下时间间隔
self.delay = round(self.every_delay/self.wx_num, 3)
# 所有需要采集的文章
self.articles = []
# 数据库操作
self.col_data = CollectionOperation(self.nickname)
# 上一次请求时间
self.pre_crawl_time = time.time()
def get_all_article(worker_num=5, process=None):
global article_data_buffer
global col_data
global front_process
global nickname
front_process = process
article_data_buffer = []
from instance import rd
nickname = rd.tidy()[0]['nickname']
col_data = CollectionOperation(nickname)
rc = RequestContent()
rc.prepare_articles(nickname,
worker_num=16,
ip_num=1,
need_proxy=use_proxy_directly())
rc.run_crawlers()
rc.join_cralwers()
TaskRecoder.print_ts()
def crawl(self):
from utils.front import message_box
from cmp.protect import Passport
if not Passport.check_password():
message_box('请先通过使用说明书中的方法获得授权有效授权证书', '授权无效 不可采集数据', 'error')
return
if len(rd.tidy()) == 0:
return
from app.api.process import Process
crange = int(self.filter['range'])
process = Process(crange)
import builtins
builtins.crawler_process = process
if crange == 0:
process.new_step()
self.crawler_article_list(process)
else:
if crange == 25:
process.new_step()
self.crawler_article_list(process)
process.new_step()
self.crawler_article(process)
else:
if crange == 50:
process.new_step()
self.crawler_article_list(process)
process.new_step()
self.crawler_reading_data(process)
else:
if crange == 75:
process.new_step()
self.crawler_article_list(process)
process.new_step()
self.crawler_article(process)
process.new_step()
self.crawler_reading_data(process)
else:
if crange == 100:
process.new_step()
self.crawler_reading_data(process)
process.send_finish()
message_box('总共用时%d分钟' % int((time.time() - self.begin_time) / 60),
'采集完成', 'success')
def __init__(self):
self.wx_req_data_list = rd.tidy()
