python D:\pymine\clean\spider_map\get_bd_uid_rest_b.py

python D:\pymine\clean\spider_map\get_bd_uid_rest.py

python D:\pymine\clean\spider_map\get_bd_uid_28_other20_b.py

#MAX_USED_TIMES = 1900
python D:\pymine\clean\spider_map\get_bd_uid_28_other20.py python D:\pymine\clean\spider_map\get_bd_uid.py python D:\pymine\clean\spider_map\get_bd_uid.py python D:\pymine\clean\spider_map\get_bd_uid.py

  

import xlrd
import time
import sys
import os
import requests
import sqlite3
import threading curPath = os.path.abspath(os.path.dirname(__file__))
rootPath = os.path.split(curPath)[0]
sys.path.append(rootPath) MAX_USED_TIMES, overrun_str, DB_KEY_EXHAUST = 1900, '天配额超限,限制访问', 'DB_KEY_EXHAUST' db = 'py_bdspider_status.db'
db = '%s\\%s' % (curPath, db) pcity_list = []
pcity_file = '%s\\%s' % (curPath, '省会城市.txt')
with open(pcity_file, 'r', encoding='utf-8') as pf:
c_ = 0
for i in pf:
c_ += 1
if c_ == 3:
c_ = 0
pcity_list.append(i.replace(' ', '').replace('\n', '') + '市')
pcity_sorted_list = sorted(pcity_list) target_city_list_big = ['广州市', '厦门市', '深圳市', '北京市', '杭州市', '成都市', '上海市', '西安市']
target_city_list_pass = target_city_list_big for i in pcity_list:
if i not in target_city_list_big:
target_city_list_pass.append(i) # def db_init_key_table():
# conn = sqlite3.connect(db)
# c = conn.cursor()
# sql = 'DELETE FROM baidu_map_key_used'
# c.execute(sql)
# conn.commit()
# pcity_file = '%s\\%s' % (curPath, 'bdmap_key.txt')
# with open(pcity_file, 'r', encoding='utf-8') as pf:
# c_ = 0
# for i in pf:
# if len(i) < 4:
# continue
# author, key = i.replace('\n', '').split('\t')
# localtime_ = time.strftime("%y%m%d%H%M%S", time.localtime())
# sql = 'INSERT INTO baidu_map_key_used (author,key,update_time,today_used) VALUES ("%s","%s","%s",%s) ' % (
# author, key, localtime_, 0)
# c.execute(sql)
# conn.commit()
# conn.close() # db_init_key_table()
# target_city_list = target_city_list[0:11]
# target_city_list = target_city_list[0:11] def db_get_one_effective():
conn = sqlite3.connect(db)
c = conn.cursor()
sql = 'SELECT key FROM baidu_map_key_used WHERE today_used<=%s ORDER BY today_used ASC' % (MAX_USED_TIMES) res = c.execute(sql).fetchone()
if res is None:
return DB_KEY_EXHAUST
else:
return res[0]
conn.close def db_update_one_today_used(key):
conn = sqlite3.connect(db)
c = conn.cursor()
localtime_ = time.strftime("%y%m%d%H%M%S", time.localtime())
sql = 'UPDATE baidu_map_key_used SET today_used = today_used+1 ,update_time=%s WHERE key="%s" ' % (
localtime_, key)
c.execute(sql)
conn.commit()
conn.close() dir_, dir_exception = 'baidu_map_uid', 'baidu_map_uid_exception'
requested_file_list = []
requested_file_dir_str, requested_file_dir_exception_str = '%s\\%s\\' % (curPath, dir_), '%s\\%s\\' % (
curPath, dir_exception)
requested_file_dir = os.listdir(requested_file_dir_str) def chk_if_requested_file():
for f in requested_file_dir:
to_in = f.split('.txt')[0]
if to_in not in requested_file_list:
requested_file_list.append(to_in) chk_if_requested_file() def write_requested_res(request_name, str_, type_='.txt'):
fname = '%s%s%s' % (requested_file_dir_str, request_name, type_)
# 上海市虹口区岳阳医院?.txt
fname = fname.replace('?', '')
with open(fname, 'w', encoding='utf-8') as ft:
ft.write(str_)
print('ok', threading.get_ident(), request_name) def write_requested_exception_res(request_name, str_, type_='.txt'):
fname = '%s%s%s' % (requested_file_dir_exception_str, request_name, type_)
# 上海市虹口区岳阳医院?.txt
fname = fname.replace('?', '')
with open(fname, 'w', encoding='utf-8') as ft:
ft.write(str_) request_dic = {} target_city_list = [] def gen_request_dic_list():
fname_source = '官方上传任务.csv_py170829093808-BD_request_name-REDUCTION170829142821'
fname_open = '%s\\%s' % (curPath, fname_source)
FEXCEL = '%s%s' % (fname_open, '.xlsx')
data = xlrd.open_workbook(FEXCEL)
table = data.sheets()[0]
nrows, ncols = table.nrows, table.ncols
for i in range(1, nrows):
l = table.row_values(i)
dbid, area_code, name_, request_name, type_, city, district, addr, street = l
# if city not in target_city_list:
# continue
if city in target_city_list_pass:
continue
if city not in target_city_list:
target_city_list.append(city)
request_name_chk = '%s%s%s' % (city, district, request_name)
if request_name_chk in requested_file_list:
continue
if city not in request_dic:
request_dic[city] = {}
if district not in request_dic[city]:
request_dic[city][district] = {}
request_dic[city][district] = []
if request_name not in request_dic[city][district]:
request_dic[city][district].append(request_name) gen_request_dic_list() fname_source = '官方上传任务.csv_py170829093808-BD_request_name-REDUCTION170829142821' # http://api.map.baidu.com/place/v2/suggestion?query=瀛嘉天下&region=重庆市&city_limit=true&output=json&ak=oy2Q7IluhhwTGlz6l8pXYv6a0m6hXxr1
base_url = 'http://api.map.baidu.com/place/v2/suggestion?query=R-QUERY&region=R-CITY&city_limit=true&output=json&ak=R-AK' def fun_(city):
for district in request_dic[city]:
for request_name in request_dic[city][district]:
request_name_chk = '%s%s%s' % (city, district, request_name)
chk_if_requested_file()
if request_name_chk in requested_file_list:
continue
ak = db_get_one_effective()
if ak == DB_KEY_EXHAUST:
print(DB_KEY_EXHAUST)
break
else:
url_ = base_url.replace('R-QUERY', request_name).replace('R-CITY', city).replace('R-AK', ak)
try:
bd_res_json_str = requests.get(url_).text
db_update_one_today_used(ak)
write_requested_res(request_name_chk, bd_res_json_str)
except Exception:
bd_res_json_str = '请求百度-异常'
write_requested_exception_res(request_name_chk, bd_res_json_str)
print(bd_res_json_str) class MyThread(threading.Thread):
def __init__(self, func, args):
threading.Thread.__init__(self)
self.func, self.args = func, args def run(self):
self.func(self.args) thread_sum = len(target_city_list) def main():
threads_list = []
for nloop in range(0, thread_sum, 1):
city = target_city_list[nloop]
thread_instance = MyThread(fun_, (city))
threads_list.append(thread_instance)
for t in threads_list:
t.setDaemon = False
t.start()
for t in threads_list:
t.join() if __name__ == '__main__':
main()

  

import xlrd
import time
import sys
import os
import requests
import sqlite3
import threading curPath = os.path.abspath(os.path.dirname(__file__))
rootPath = os.path.split(curPath)[0]
sys.path.append(rootPath) MAX_USED_TIMES, overrun_str, DB_KEY_EXHAUST = 1900, '天配额超限,限制访问', 'DB_KEY_EXHAUST' db = 'py_bdspider_status.db'
db = '%s\\%s' % (curPath, db) pcity_list = []
pcity_file = '%s\\%s' % (curPath, '省会城市.txt')
with open(pcity_file, 'r', encoding='utf-8') as pf:
c_ = 0
for i in pf:
c_ += 1
if c_ == 3:
c_ = 0
pcity_list.append(i.replace(' ', '').replace('\n', '') + '市')
pcity_sorted_list = sorted(pcity_list) target_city_list_big = ['广州市', '厦门市', '深圳市', '北京市', '杭州市', '成都市', '上海市', '西安市']
target_city_list = [] for i in pcity_list:
if i not in target_city_list_big:
target_city_list.append(i) # def db_init_key_table():
# conn = sqlite3.connect(db)
# c = conn.cursor()
# sql = 'DELETE FROM baidu_map_key_used'
# c.execute(sql)
# conn.commit()
# pcity_file = '%s\\%s' % (curPath, 'bdmap_key.txt')
# with open(pcity_file, 'r', encoding='utf-8') as pf:
# c_ = 0
# for i in pf:
# if len(i) < 4:
# continue
# author, key = i.replace('\n', '').split('\t')
# localtime_ = time.strftime("%y%m%d%H%M%S", time.localtime())
# sql = 'INSERT INTO baidu_map_key_used (author,key,update_time,today_used) VALUES ("%s","%s","%s",%s) ' % (
# author, key, localtime_, 0)
# c.execute(sql)
# conn.commit()
# conn.close() # db_init_key_table()
target_city_list = target_city_list[11:] def db_get_one_effective():
conn = sqlite3.connect(db)
c = conn.cursor()
sql = 'SELECT key FROM baidu_map_key_used WHERE today_used<=%s ' % (MAX_USED_TIMES)
res = c.execute(sql).fetchone()
if res is None:
return DB_KEY_EXHAUST
else:
return res[0]
conn.close def db_update_one_today_used(key):
conn = sqlite3.connect(db)
c = conn.cursor()
localtime_ = time.strftime("%y%m%d%H%M%S", time.localtime())
sql = 'UPDATE baidu_map_key_used SET today_used = today_used+1 ,update_time=%s WHERE key="%s" ' % (
localtime_, key)
c.execute(sql)
conn.commit()
conn.close() dir_, dir_exception = 'baidu_map_uid', 'baidu_map_uid_exception'
requested_file_list = []
requested_file_dir_str, requested_file_dir_exception_str = '%s\\%s\\' % (curPath, dir_), '%s\\%s\\' % (
curPath, dir_exception)
requested_file_dir = os.listdir(requested_file_dir_str) def chk_if_requested_file():
for f in requested_file_dir:
to_in = f.split('.txt')[0]
if to_in not in requested_file_list:
requested_file_list.append(to_in) chk_if_requested_file() def write_requested_res(request_name, str_, type_='.txt'):
fname = '%s%s%s' % (requested_file_dir_str, request_name, type_)
# 上海市虹口区岳阳医院?.txt
fname = fname.replace('?', '')
with open(fname, 'w', encoding='utf-8') as ft:
ft.write(str_)
print('ok', threading.get_ident(), request_name) def write_requested_exception_res(request_name, str_, type_='.txt'):
fname = '%s%s%s' % (requested_file_dir_exception_str, request_name, type_)
# 上海市虹口区岳阳医院?.txt
fname = fname.replace('?', '')
with open(fname, 'w', encoding='utf-8') as ft:
ft.write(str_) request_dic = {} def gen_request_dic_list():
fname_source = '官方上传任务.csv_py170829093808-BD_request_name-REDUCTION170829142821'
fname_open = '%s\\%s' % (curPath, fname_source)
FEXCEL = '%s%s' % (fname_open, '.xlsx')
data = xlrd.open_workbook(FEXCEL)
table = data.sheets()[0]
nrows, ncols = table.nrows, table.ncols
for i in range(1, nrows):
l = table.row_values(i)
dbid, area_code, name_, request_name, type_, city, district, addr, street = l
if city not in target_city_list:
continue
request_name_chk = '%s%s%s' % (city, district, request_name)
if request_name_chk in requested_file_list:
continue
if city not in request_dic:
request_dic[city] = {}
if district not in request_dic[city]:
request_dic[city][district] = {}
request_dic[city][district] = []
if request_name not in request_dic[city][district]:
request_dic[city][district].append(request_name) gen_request_dic_list() fname_source = '官方上传任务.csv_py170829093808-BD_request_name-REDUCTION170829142821' # http://api.map.baidu.com/place/v2/suggestion?query=瀛嘉天下&region=重庆市&city_limit=true&output=json&ak=oy2Q7IluhhwTGlz6l8pXYv6a0m6hXxr1
base_url = 'http://api.map.baidu.com/place/v2/suggestion?query=R-QUERY&region=R-CITY&city_limit=true&output=json&ak=R-AK' def fun_(city):
for district in request_dic[city]:
for request_name in request_dic[city][district]:
request_name_chk = '%s%s%s' % (city, district, request_name)
chk_if_requested_file()
if request_name_chk in requested_file_list:
continue
ak = db_get_one_effective()
if ak == DB_KEY_EXHAUST:
print(DB_KEY_EXHAUST)
break
else:
url_ = base_url.replace('R-QUERY', request_name).replace('R-CITY', city).replace('R-AK', ak)
try:
bd_res_json_str = requests.get(url_).text
db_update_one_today_used(ak)
write_requested_res(request_name_chk, bd_res_json_str)
except Exception:
bd_res_json_str = '请求百度-异常'
write_requested_exception_res(request_name_chk, bd_res_json_str)
print(bd_res_json_str) class MyThread(threading.Thread):
def __init__(self, func, args):
threading.Thread.__init__(self)
self.func, self.args = func, args def run(self):
self.func(self.args) thread_sum = len(target_city_list) def main():
threads_list = []
for nloop in range(0, thread_sum, 1):
city = target_city_list[nloop]
if city not in request_dic:
continue
thread_instance = MyThread(fun_, (city))
threads_list.append(thread_instance)
for t in threads_list:
t.setDaemon = False
t.start()
for t in threads_list:
t.join() if __name__ == '__main__':
main()
import xlrd
import time
import sys
import os
import requests
import sqlite3
import threading curPath = os.path.abspath(os.path.dirname(__file__))
rootPath = os.path.split(curPath)[0]
sys.path.append(rootPath) MAX_USED_TIMES, overrun_str, DB_KEY_EXHAUST = 1900, '天配额超限,限制访问', 'DB_KEY_EXHAUST' db = 'py_bdspider_status.db'
db = '%s\\%s' % (curPath, db) pcity_list = []
pcity_file = '%s\\%s' % (curPath, '省会城市.txt')
with open(pcity_file, 'r', encoding='utf-8') as pf:
c_ = 0
for i in pf:
c_ += 1
if c_ == 3:
c_ = 0
pcity_list.append(i.replace(' ', '').replace('\n', '') + '市')
pcity_sorted_list = sorted(pcity_list) target_city_list_big = ['广州市', '厦门市', '深圳市', '北京市', '杭州市', '成都市', '上海市', '西安市']
target_city_list = [] for i in pcity_list:
if i not in target_city_list_big:
target_city_list.append(i) # def db_init_key_table():
# conn = sqlite3.connect(db)
# c = conn.cursor()
# sql = 'DELETE FROM baidu_map_key_used'
# c.execute(sql)
# conn.commit()
# pcity_file = '%s\\%s' % (curPath, 'bdmap_key.txt')
# with open(pcity_file, 'r', encoding='utf-8') as pf:
# c_ = 0
# for i in pf:
# if len(i) < 4:
# continue
# author, key = i.replace('\n', '').split('\t')
# localtime_ = time.strftime("%y%m%d%H%M%S", time.localtime())
# sql = 'INSERT INTO baidu_map_key_used (author,key,update_time,today_used) VALUES ("%s","%s","%s",%s) ' % (
# author, key, localtime_, 0)
# c.execute(sql)
# conn.commit()
# conn.close() # db_init_key_table()
# target_city_list = target_city_list[0:11]
# target_city_list = target_city_list[0:11]
target_city_list =target_city_list[11:] def db_get_one_effective():
conn = sqlite3.connect(db)
c = conn.cursor()
sql = 'SELECT key FROM baidu_map_key_used WHERE today_used<=%s ORDER BY today_used ASC' % (MAX_USED_TIMES) res = c.execute(sql).fetchone()
if res is None:
return DB_KEY_EXHAUST
else:
return res[0]
conn.close def db_update_one_today_used(key):
conn = sqlite3.connect(db)
c = conn.cursor()
localtime_ = time.strftime("%y%m%d%H%M%S", time.localtime())
sql = 'UPDATE baidu_map_key_used SET today_used = today_used+1 ,update_time=%s WHERE key="%s" ' % (
localtime_, key)
c.execute(sql)
conn.commit()
conn.close() dir_, dir_exception = 'baidu_map_uid', 'baidu_map_uid_exception'
requested_file_list = []
requested_file_dir_str, requested_file_dir_exception_str = '%s\\%s\\' % (curPath, dir_), '%s\\%s\\' % (
curPath, dir_exception)
requested_file_dir = os.listdir(requested_file_dir_str) def chk_if_requested_file():
for f in requested_file_dir:
to_in = f.split('.txt')[0]
if to_in not in requested_file_list:
requested_file_list.append(to_in) chk_if_requested_file() def write_requested_res(request_name, str_, type_='.txt'):
fname = '%s%s%s' % (requested_file_dir_str, request_name, type_)
# 上海市虹口区岳阳医院?.txt
fname = fname.replace('?', '')
with open(fname, 'w', encoding='utf-8') as ft:
ft.write(str_)
print('ok', threading.get_ident(), request_name) def write_requested_exception_res(request_name, str_, type_='.txt'):
fname = '%s%s%s' % (requested_file_dir_exception_str, request_name, type_)
# 上海市虹口区岳阳医院?.txt
fname = fname.replace('?', '')
with open(fname, 'w', encoding='utf-8') as ft:
ft.write(str_) request_dic = {} def gen_request_dic_list():
fname_source = '官方上传任务.csv_py170829093808-BD_request_name-REDUCTION170829142821'
fname_open = '%s\\%s' % (curPath, fname_source)
FEXCEL = '%s%s' % (fname_open, '.xlsx')
data = xlrd.open_workbook(FEXCEL)
table = data.sheets()[0]
nrows, ncols = table.nrows, table.ncols
for i in range(1, nrows):
l = table.row_values(i)
dbid, area_code, name_, request_name, type_, city, district, addr, street = l
if city not in target_city_list:
continue
request_name_chk = '%s%s%s' % (city, district, request_name)
if request_name_chk in requested_file_list:
continue
if city not in request_dic:
request_dic[city] = {}
if district not in request_dic[city]:
request_dic[city][district] = {}
request_dic[city][district] = []
if request_name not in request_dic[city][district]:
request_dic[city][district].append(request_name) gen_request_dic_list() fname_source = '官方上传任务.csv_py170829093808-BD_request_name-REDUCTION170829142821' # http://api.map.baidu.com/place/v2/suggestion?query=瀛嘉天下&region=重庆市&city_limit=true&output=json&ak=oy2Q7IluhhwTGlz6l8pXYv6a0m6hXxr1
base_url = 'http://api.map.baidu.com/place/v2/suggestion?query=R-QUERY&region=R-CITY&city_limit=true&output=json&ak=R-AK' def fun_(city):
for district in request_dic[city]:
for request_name in request_dic[city][district]:
request_name_chk = '%s%s%s' % (city, district, request_name)
chk_if_requested_file()
if request_name_chk in requested_file_list:
continue
ak = db_get_one_effective()
if ak == DB_KEY_EXHAUST:
print(DB_KEY_EXHAUST)
break
else:
url_ = base_url.replace('R-QUERY', request_name).replace('R-CITY', city).replace('R-AK', ak)
try:
bd_res_json_str = requests.get(url_).text
db_update_one_today_used(ak)
write_requested_res(request_name_chk, bd_res_json_str)
except Exception:
bd_res_json_str = '请求百度-异常'
write_requested_exception_res(request_name_chk, bd_res_json_str)
print(bd_res_json_str) class MyThread(threading.Thread):
def __init__(self, func, args):
threading.Thread.__init__(self)
self.func, self.args = func, args def run(self):
self.func(self.args) thread_sum = len(target_city_list) def main():
threads_list = []
for nloop in range(0, thread_sum, 1):
city = target_city_list[nloop]
thread_instance = MyThread(fun_, (city))
threads_list.append(thread_instance)
for t in threads_list:
t.setDaemon = False
t.start()
for t in threads_list:
t.join() if __name__ == '__main__':
main()

  

ORDER BY today_used ASC' % (MAX_USED_TIMES)的更多相关文章

  1. order by id asc得出的排序是什么原理

    我们要用order by id asc得出的排序应该是,4,好了原理就这么简. sql实现方法,代码如下: : 代码如下: $sql ="Select 字段 from 表名 where id ...

  2. select * from (select P.*,ROWNUM RN FROM(select * from Mp_Relatedart where pubbaseid=785 order by ID ASC )P)M WHERE M.RN>2 and M.RN <= 7

    select * from (select P.*,ROWNUM RN FROM(select * from Mp_Relatedart where pubbaseid=785 order by ID ...

  3. oracle的row_number() OVER (ORDER BY COL2 asc)和row_number() OVER (PARTITION BY COL1 ORDER BY COL2)的用法

    转自:https://jingyan.baidu.com/article/9989c74604a644f648ecfef3.html SELECT ROW_NUMBER() OVER(PARTITIO ...

  4. json.dumps(i['bd_res'], ensure_ascii=False)

    json.dumps(i['bd_res'], ensure_ascii=False) import xlrd import time import sys import os import requ ...

  5. csv .xlsx

    def gen_file_data(fodir, fname, sheet_index=0, ): if fname.find('.xlsx') > -1: fname_open = '%s\\ ...

  6. rm_invalid_file

    import xlrd import time import sys import os import requests import sqlite3 import threading curPath ...

  7. 谈谈MySQL中的降序索引 order by id DESC / ASC

    今天这篇主要讲order by 语句中的多个字段asc desc的问题.mysql5中,索引存储的排序方式是ASC的,没有DESC的索引.现在能够理解为啥order by 默认是按照ASC来排序的了吧 ...

  8. Oracle查询排序asc/desc 多列 order by

    查询结果的排序 显示EMP表中不同的部门编号. 如果要在查询的同时排序显示结果,可以使用如下的语句: SELECT 字段列表 FROM 表名 WHERE 条件 ORDER BY 字段名1 [ASC|D ...

  9. Oracle 查询语句(where,order by ,like,in,distinct)

    select * from production;alter table production add productionprice number(7,2); UPDATE production s ...

随机推荐

  1. ECSHOP去版权(删除ECSHOP所有标识)

    前台部分: 1:去掉头部TITLE部分的ECSHOP演示站 Powered by ecshop前者”ECSHOP演示站”在后台商店设置 – 商店标题修改后者” Powered by ecshop”打开 ...

  2. EffectiveJava(11)Java中的clone

    java中的clone clone构造器及其静态工厂的变形 优点:它们不依赖于某一种很有风险的,语言之外的对象创建机制; 它们不要求遵守尚未制定好文档的规范 他们不会于final域的正常使用发生冲突 ...

  3. 安装openstack 时 遇见的一些问题及解决方法!

    感谢朋友支持本博客,欢迎共同探讨交流.因为能力和时间有限,错误之处在所难免.欢迎指正! 假设转载.请保留作者信息. 博客地址:http://blog.csdn.net/qq_21398167 原博文地 ...

  4. Windows为什么双击打开‘我的电脑’, 没有了‘前进’‘ 后退’‘向上’等按钮?

    如图所示   点击查看 工具栏 标准按钮即可   左侧的数值虚线可以拖动到任意,还可以添加按钮如搜索,删除,复制,剪切等

  5. 微信小程序 - 文字换行问题

    css word-break: break-all;

  6. python——双下划线与python命名机制

    python中双下划线的作用(1)所有以双下划线开头的成员是私有的(2)python对于私有变量是会进行扎压(mangling)的,扎压规则是原始定义:class A():    __function ...

  7. C语言中使用库函数解析命令行参数

    在编写需要命令行参数的C程序的时候,往往我们需要先解析命令行参数,然后根据这些参数来启动我们的程序. C的库函数中提供了两个函数可以用来帮助我们解析命令行参数:getopt.getopt_long. ...

  8. handlebars.js基础学习笔记

    最近在帮学校做个课程网站,就有人推荐用jquery+ajax+handlebars做网站前端,刚接触发现挺高大上的,于是就把一些基础学习笔记记录下来啦. 1.引用文件: jquery.js文件下载:h ...

  9. 多trac的安装和配置

    其他相关网页: trac+svn: http://wenku.baidu.com/view/84389a81ec3a87c24028c43f.html apache(GCI):http://hi.ba ...

  10. NSNotification的几点说明

    1.NSNotification消息的同步性 ①NSNotification使用的是同步操作.即如果你在程序中的A位置post了一个NSNotification,在B位置注册了一个observer,通 ...