Skip to content

Z
zzsn_spider
提交 caa3a936 作者: LiuLiYuan
操作

Merge remote-tracking branch 'origin/master' 

# Conflicts:
#	base/BaseCore.py
上级 21214964 0b2f4ac1
正在显示 包含 324 行增加 和 342 行删除
base/BaseCore.py
......@@ -15,15 +15,15 @@ from selenium.webdriver.chrome.service import Service
from openpyxl import Workbook
import langid
# 注意 程序退出前 调用BaseCore.close() 关闭相关资源
class BaseCore:
# 序列号
__seq = 0
# 代理池 数据库连接
__cnx_proxy = None
__cnx_proxy =None
__cursor_proxy = None
# agent 池
__USER_AGENT_LIST = [
......@@ -218,9 +218,8 @@ class BaseCore:
'Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5'
]
# Android agent池
__USER_PHONE_AGENT_LIST = [
'Mozilla/5.0 (Linux; Android 7.1.1; OPPO R9sk) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.111 Mobile Safari/537.36']
#Android agent池
__USER_PHONE_AGENT_LIST = ['Mozilla/5.0 (Linux; Android 7.1.1; OPPO R9sk) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.111 Mobile Safari/537.36']
def __init__(self):
self.__cnx_proxy = pymysql.connect(host='114.115.159.144', user='root', password='zzsn9988', db='clb_project',
......@@ -239,11 +238,12 @@ class BaseCore:
self.__cnx_proxy.close()
self.cursor.close()
self.cnx.close()
except:
except :
pass
# 计算耗时
def getTimeCost(self, start, end):
def getTimeCost(self,start, end):
seconds = int(end - start)
m, s = divmod(seconds, 60)
h, m = divmod(m, 60)
......@@ -256,7 +256,6 @@ class BaseCore:
else:
ms = int((end - start) * 1000)
return "%d毫秒" % (ms)
# 当前时间格式化
# 1 : 2001-01-01 12:00:00 %Y-%m-%d %H:%M:%S
# 2 : 010101120000 %y%m%d%H%M%S
......@@ -286,7 +285,7 @@ class BaseCore:
return "ZZSN" + self.getNowTime(2) + str(self.__seq).zfill(3)
# 日志格式
def logFormate(self, record, handler):
def logFormate(self,record, handler):
formate = "[{date}] [{level}] [{filename}] [{func_name}] [{lineno}] {msg}".format(
date=record.time, # 日志时间
level=record.level_name, # 日志等级
......@@ -296,9 +295,8 @@ class BaseCore:
msg=record.message # 日志内容
)
return formate
# 获取logger
def getLogger(self, fileLogFlag=True, stdOutFlag=True):
def getLogger(self,fileLogFlag=True, stdOutFlag=True):
dirname, filename = os.path.split(os.path.abspath(sys.argv[0]))
dirname = os.path.join(dirname, "logs")
filename = filename.replace(".py", "") + ".log"
......@@ -347,34 +345,34 @@ class BaseCore:
proxy_list.append(proxy)
return proxy_list[random.randint(0, 3)]
# 字符串截取
def getSubStr(self, str, beginStr, endStr):
if beginStr == '':
#字符串截取
def getSubStr(self,str,beginStr,endStr):
if beginStr=='':
pass
else:
begin = str.find(beginStr)
if begin == -1:
begin = 0
str = str[begin:]
if endStr == '':
begin=str.find(beginStr)
if begin==-1:
begin=0
str=str[begin:]
if endStr=='':
pass
else:
end = str.rfind(endStr)
if end == -1:
end=str.rfind(endStr)
if end==-1:
pass
else:
str = str[0:end + 1]
str = str[0:end+1]
return str
# 繁体字转简体字
def hant_2_hans(self, hant_str: str):
def hant_2_hans(self,hant_str: str):
'''
Function: 将 hant_str 由繁体转化为简体
'''
return zhconv.convert(hant_str, 'zh-hans')
# 判断字符串里是否含数字
def str_have_num(self, str_num):
def str_have_num(self,str_num):
panduan = False
for str_1 in str_num:
......@@ -394,7 +392,7 @@ class BaseCore:
# return gw_item.decode() if gw_item else None
# 从Redis的List中获取并移除一个元素
def redicPullData(self, key):
def redicPullData(self,key):
item = self.r.lpop(key)
return item.decode() if item else None
......@@ -417,7 +415,7 @@ class BaseCore:
chrome_options = webdriver.ChromeOptions()
if headless:
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
chrome_options.add_argument('--disable-gpu')
chrome_options.add_experimental_option(
"excludeSwitches", ["enable-automation"])
chrome_options.add_experimental_option('useAutomationExtension', False)
......@@ -460,16 +458,16 @@ class BaseCore:
print(e)
self.cnx.commit()
# 获取企查查token
#获取企查查token
def GetToken(self):
# 获取企查查token
#获取企查查token
query = "select token from QCC_token "
# token = '67ec7402166df1da84ae83c4b95cefc0' # 需要隔两个小时左右抓包修改
self.cursor.execute(query)
token = self.cursor.fetchone()[0]
return token
# 检测语言
#检测语言
def detect_language(self, text):
# 使用langid.py判断文本的语言
result = langid.classify(text)
......@@ -479,11 +477,11 @@ class BaseCore:
return 'cn'
return result[0]
# 追加接入excel
def writerToExcel(self, detailList, filename):
#追加接入excel
def writerToExcel(self,detailList,filename):
# filename='baidu搜索.xlsx'
# 读取已存在的xlsx文件
existing_data = pd.read_excel(filename, engine='openpyxl')
existing_data = pd.read_excel(filename,engine='openpyxl')
# 创建新的数据
new_data = pd.DataFrame(data=detailList)
# 将新数据添加到现有数据的末尾
......@@ -492,6 +490,8 @@ class BaseCore:
combined_data.to_excel(filename, index=False)
# return combined_data
# 对失败或者断掉的企业 重新放入redis
def rePutIntoR(self, item):
#对失败或者断掉的企业 重新放入redis
def rePutIntoR(self,item):
self.r.rpush('NewsEnterprise:gwqy_socialCode', item)
comData/weixin_solo/oneWeixin.py
# -*- coding: utf-8 -*-
'''
记录一天能采多少公众号
记录一天能采多少公众号,建一个数据库表 更新公众号的状态
'''
import requests, time, random, json, pymysql, redis
......@@ -17,13 +18,17 @@ from base.BaseCore import BaseCore
import os
baseCore = BaseCore()
log = baseCore.getLogger()
cnx_ = baseCore.cnx
cursor_ = baseCore.cursor
cnx = pymysql.connect(host="114.116.44.11", user="root", password="f7s0&7qqtK", db="clb_project", charset="utf8mb4")
cursor = cnx.cursor()
r = baseCore.r
urllib3.disable_warnings()
def check_url(sid, article_url):
r = redis.Redis(host="114.115.236.206", port=6379, password='clbzzsn')
res = r.sismember(f'wx_url_{sid}', article_url) # 注意是 保存set的方式
res = r.sismember(f'wx_url_{sid}',article_url)
if res == 1:
return True
else:
......@@ -63,7 +68,7 @@ def get_proxy():
return proxy_list
def get_info(json_search):
def get_info(sid,json_search):
num_caiji = 0
kaishi_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
obsClient = ObsClient(
......@@ -81,9 +86,9 @@ def get_info(json_search):
url_news = one_news['link']
# url_ft = check_url(sid, url_news)
# if url_ft:
# return list_all_info,url_news,news_title
url_ft = check_url(sid, url_news)
if url_ft:
return list_all_info,num_caiji
try:
res_news = requests.get(url_news, timeout=20)
except:
......@@ -97,10 +102,24 @@ def get_info(json_search):
del news_html['class']
except:
pass
news_content = news_html.text
try:
news_content = news_html.text
except:
log.info(f'--------内容为空--------{url_news}--------')
time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
false = [
news_title,
url_news,
news_html,
'文章内容为空',
time_now
]
insertSql = f"insert into WeixinGZH (site_name,site_url,json_error_info,error_type,create_time) values (%s,%s,%s,%s,%s)"
cursor_.execute(insertSql, tuple(false))
cnx_.commit()
continue
list_img = news_html.find_all('img')
for num_img in range(len(list_img)):
img_one = list_img[num_img]
......@@ -149,18 +168,19 @@ def get_info(json_search):
'source': '11',
'createDate': time_now
}
# for nnn in range(0, 3):
# try:
# producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'])
# kafka_result = producer.send("crawlerInfo", json.dumps(dic_info, ensure_ascii=False).encode('utf8'))
# kafka_time_out = kafka_result.get(timeout=10)
# # add_url(sid, url_news)
# break
# except:
# time.sleep(5)
# continue
for nnn in range(0, 3):
try:
producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'])
kafka_result = producer.send("crawlerInfo", json.dumps(dic_info, ensure_ascii=False).encode('utf8'))
kafka_time_out = kafka_result.get(timeout=10)
# add_url(sid, url_news)
break
except:
time.sleep(5)
continue
num_caiji = num_caiji + 1
list_all_info.append(dic_info)
time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
dic_info2 = {
'infoSourceId': sid,
......@@ -171,16 +191,45 @@ def get_info(json_search):
'dispatcherStatus': '1',
'source': '1',
}
# for nnn2 in range(0, 3):
# try:
# producer2 = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'])
# kafka_result2 = producer2.send("collectionAndDispatcherInfo",
# json.dumps(dic_info2, ensure_ascii=False).encode('utf8'))
# break
# except:
# time.sleep(5)
# continue
return list_all_info,url_news,news_title
for nnn2 in range(0, 3):
try:
producer2 = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'])
kafka_result2 = producer2.send("collectionAndDispatcherInfo",
json.dumps(dic_info2, ensure_ascii=False).encode('utf8'))
break
except:
time.sleep(5)
continue
return list_all_info,num_caiji
#定时
def getFromSql():
selectSql = "SELECT info_source_code from info_source where site_uri like '%mp.weixin.qq.com%'"
cursor.execute(selectSql)
results = cursor.fetchall()
result_list = [item[0] for item in results]
#放入redis
for item in result_list:
r.rpush('WeiXinGZH:infoSourceCode', item)
#刷新浏览器并获得token
def flushAndGetToken(list_b):
browser_run = list_b[0]
log.info('======刷新浏览器=====')
browser_run.refresh()
cookie_list = browser_run.get_cookies()
cur_url = browser_run.current_url
token = cur_url.split('token=')[1]
log.info(f'===========当前token为：{token}============')
cookies = {}
for cookie in cookie_list:
cookies[cookie['name']] = cookie['value']
return token,cookies
#采集失败的公众号 重新放入redis
def rePutIntoR(item):
r.rpush('WeiXinGZH:infoSourceCode', item)
if __name__=="__main__":
......@@ -195,288 +244,212 @@ if __name__=="__main__":
opt = webdriver.ChromeOptions()
opt.add_argument(
'user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36')
# opt.add_argument(f"--proxy-server={ip}")
opt.add_argument("--ignore-certificate-errors")
opt.add_argument("--ignore-ssl-errors")
opt.add_experimental_option("excludeSwitches", ["enable-automation"])
opt.add_experimental_option('excludeSwitches', ['enable-logging'])
opt.add_experimental_option('useAutomationExtension', False)
opt.binary_location =r'D:\crawler\baidu_crawler\tool\Google\Chrome\Application\chrome.exe'
chromedriver = r'C:\Users\WIN10\DataspellProjects\crawlerProjectDemo\tmpcrawler\cmd100\chromedriver.exe'
# opt.binary_location =r'D:\crawler\baidu_crawler\tool\Google\Chrome\Application\chrome.exe'
# chromedriver = r'C:\Users\WIN10\DataspellProjects\crawlerProjectDemo\tmpcrawler\cmd100\chromedriver.exe'
chromedriver = r'D:/chrome/chromedriver.exe'
browser1 = webdriver.Chrome(chrome_options=opt, executable_path=chromedriver)
list_b = [browser1]
url = "https://mp.weixin.qq.com/"
browser1.get(url)
# browser2.get(url)
# browser3.get(url)
# 可改动
time.sleep(30)
num_b = 0
browser_run = list_b[0]
log.info('======刷新浏览器=====')
browser_run.refresh()
cookie_list = browser_run.get_cookies()
cur_url = browser_run.current_url
token = cur_url.split('token=')[1]
log.info(f'===========当前token为：{token}============')
cookies = {}
for cookie in cookie_list:
cookies[cookie['name']] = cookie['value']
# todo:从数据库里读信息，放入redis，定时任务 每天放入数据
# getFromSql()
s = requests.session()
# 记录运行公众号的个数
count = 0
while True:
all = []
# 刷新浏览器并获取当前token和cookie
token, cookies = flushAndGetToken(list_b)
list_all_info = []
list_error_url = []
list_laiyuan = []
cnx = pymysql.connect(host="114.116.44.11", user="root", password="f7s0&7qqtK", db="clb_project", charset="utf8mb4")
log.info('===========获取公众号============')
start_ = time.time()
with cnx.cursor() as cursor:
sql = "SELECT site_uri,id,site_name,info_source_code from info_source where site_uri like '%mp.weixin.qq.com%'"
cursor.execute(sql)
rows = cursor.fetchall()
# 将数据库中的数据切分为两部分
for row in rows:
# print(len(rows[:945]))
# if row[2]=='南方周末':
dic_url = {
'url': row[0],
'sid': row[1],
'name': row[2],
'info_source_code': row[3],
'biz': ''
}
list_laiyuan.append(dic_url)
log.info(f'===========获取公众号完成，耗时{baseCore.getTimeCost(start_,time.time())}============')
# list_laiyuan.reverse()
# #todo:redis中数据 pop一条
infoSourceCode = baseCore.redicPullData('WeiXinGZH:infoSourceCode')
if infoSourceCode == 'None':
#当一次采集完之后，重新插入数据并等待插入完成
getFromSql()
time.sleep(20)
log.info(f'========本次公众号已采集完毕，共采集{count}个公众号=========总耗时：{baseCore.getTimeCost(start_,time.time())}')
continue
sql = f"SELECT site_uri,id,site_name,info_source_code from info_source where info_source_code = '{infoSourceCode}' "
# '一带一路百人论坛'
# sql = f"SELECT site_uri,id,site_name,info_source_code from info_source where site_name = '一带一路百人论坛' "
cursor.execute(sql)
row = cursor.fetchone()
dic_url = {
'url_': row[0],
'sid': row[1],
'name': row[2],
'info_source_code': row[3],
'biz': ''
}
log.info('===========获取biz==========')
start__ = time.time()
for dic_one in list_laiyuan:
url = dic_one['url']
try:
biz = url.split('__biz=')[1].split('==&')[0].split('=')[0]
dic_one['biz'] = biz
except:
continue
log.info(f'==========获取biz完成，耗时{baseCore.getTimeCost(start__,time.time())}==========')
# list_biz.append(biz)
# list_laiyuan.reverse()
#记录错误的biz及相关信息
biz_error_biz = []
biz_error_origin = []
biz_error_code = []
#记录解析成功但采集失败的相关信息
get_error_biz = []
get_error_origin = []
get_error_code = []
#记录解析失败的相关信息
json_error_biz = []
json_error_origin = []
json_error_code = []
for num_biz in range(0, len(list_laiyuan)):
browser_run.refresh()
cookie_list = browser_run.get_cookies()
cur_url = browser_run.current_url
token = cur_url.split('token=')[1]
s.cookies.update(cookies)
url_ = dic_url['url_']
origin = dic_url['name']
info_source_code = dic_url['info_source_code']
sid = dic_url['sid']
try:
biz = url_.split('__biz=')[1].split('==&')[0].split('=')[0]
dic_url['biz'] = biz
except Exception as e:
log.info(f'---公众号--{origin}---biz错误')
time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
log.info(f'=========刷新时间:{time_now}=========')
log.info(f'=========当前token为:{token}=========')
cookies = {}
for cookie in cookie_list:
cookies[cookie['name']] = cookie['value']
list_url = []
s.cookies.update(cookies)
sid = list_laiyuan[num_biz]['sid']
origin = list_laiyuan[num_biz]['name']
info_source_code = list_laiyuan[num_biz]['info_source_code']
biz = list_laiyuan[num_biz]['biz']
if biz:
pass
else:
continue
fakeid = biz + '=='
url_search = f'https://mp.weixin.qq.com/cgi-bin/appmsg?action=list_ex&begin=5&count=5&fakeid={fakeid}&type=9&query=&token={token}&lang=zh_CN&f=json&ajax=1'
error = [
origin,
url_,
info_source_code,
e,
'biz错误',
time_now
]
insertSql = f"insert into WeixinGZH (site_name,site_url,info_source_code,json_error_info,error_type,create_time) values (%s,%s,%s,%s,%s,%s)"
cursor_.execute(insertSql, tuple(error))
cnx_.commit()
continue
fakeid = biz + '=='
try:
ip = get_proxy()[random.randint(0, 3)]
json_search = s.get(url_search, headers=headers, proxies=ip,
verify=False).json() # , proxies=ip, verify=False
time.sleep(2)
url_search = f'https://mp.weixin.qq.com/cgi-bin/appmsg?action=list_ex&begin=5&count=5&fakeid={fakeid}&type=9&query=&token={token}&lang=zh_CN&f=json&ajax=1'
try:
ip = get_proxy()[random.randint(0, 3)]
json_search = s.get(url_search, headers=headers, proxies=ip,
verify=False).json() # , proxies=ip, verify=False
str_t = json.dumps(json_search)
time.sleep(2)
except:
log.info(f'===公众号{origin}请求失败！当前时间：{baseCore.getNowTime(1)}===')
# error_text = str(json_search)
json_search = ''
aa = time.sleep(600)
log.info(f'======等待时间{aa}=======')
break
try:
list_all = json_search['app_msg_list']
except:
#解析失败的情况
count += 1
# (f'{fakeid}:biz错误！')
log.info(f'{fakeid}:biz错误！、公众号为{origin}=====当前时间：{baseCore.getNowTime(1)}')
biz_error_biz.append(biz)
biz_error_origin.append(origin)
biz_error_code.append(info_source_code)
df_error_biz = pd.DataFrame({'公众号': biz_error_origin,
'code': biz_error_code,
'错误biz': biz_error_biz,
})
excel_name = time.strftime("%Y-%m-%d", time.localtime())
#原来：
# df_error_biz.to_excel(f'./错误biz/{excel_name}.xlsx', index=False)
#改为：
file_path = f'./错误biz/{excel_name}.xlsx'
if os.path.exists(file_path):
pass
else:
workbook = Workbook()
workbook.save(file_path)
workbook.close()
# with pd.ExcelWriter(file_path, engine='xlsxwriter',
# options={'strings_to_urls': False}) as writer:
baseCore.writerToExcel(df_error_biz, file_path)
# combined_data.to_excel(writer, index=False)
bb = time.sleep(3600)
log.info(f'========当前账号可能被封，等待时长{bb}======')
except:
log.error(f'===公众号{origin}请求失败！当前时间：{baseCore.getNowTime(1)}===')
rePutIntoR(info_source_code)
continue
#{"base_resp": {"ret": 200003, "err_msg": "invalid session"}}
# TODO:需要判断返回值，根据返回值判断是封号还是biz错误
# {'base_resp': {'err_msg': 'freq control', 'ret': 200013}}========= 封号
# {'base_resp': {'err_msg': 'invalid args', 'ret': 200002}} 公众号biz错误 链接
# 'base_resp': {'err_msg': 'ok', 'ret': 0} 正常
ret = json_search['base_resp']['ret']
if ret == 0:
pass
elif ret == 200013:
# 重新放入redis
# time.sleep(3600)
# 刷新 暂时用一下方法
rePutIntoR(info_source_code)
log.info(f'======该账号被封=======')
for i in range(0,6): #600,1200,1800,2400,3000,3600
#刷新
log.info(f'=============刷新浏览器=============')
wait_time = time.sleep(600)
log.info(f'=======等待时间{wait_time}秒=====刷新浏览器=====')
browser_run = list_b[0]
browser_run.refresh()
cookie_list = browser_run.get_cookies()
cur_url = browser_run.current_url
token = cur_url.split('token=')[1]
log.info(f'=========当前token:{token}=========')
cookies = {}
for cookie in cookie_list:
cookies[cookie['name']] = cookie['value']
continue
if list_all:
str_t = json.dumps(json_search)
try:
list_all_info,url_news,news_title = get_info(json_search)
time.sleep(2)
count += 1
if len(list_all_info):
for dic_one in list_all_info:
all.append(dic_one)
# df_info = pd.DataFrame(all)
excel_name = time.strftime("%Y-%m-%d", time.localtime())
try:
file_path = f'./运行结果/{excel_name}_实时数据.xlsx'
if os.path.exists(file_path):
pass
else:
workbook = Workbook()
workbook.save(file_path)
workbook.close()
# df_info.to_excel(f'./运行结果/{excel_name}_实时数据.xlsx', index=False)
# with pd.ExcelWriter(file_path, engine='xlsxwriter',
# options={'strings_to_urls': False}) as writer:
baseCore.writerToExcel(all,file_path)
# combined_data.to_excel(writer, index=False)
except:
file_path = f'./运行结果/{excel_name}_2_实时数据.xlsx'
if os.path.exists(file_path):
pass
else:
workbook = Workbook()
workbook.save(file_path)
workbook.close()
# df_info.to_excel(f'./运行结果/{excel_name}_2_实时数据.xlsx', index=False)
# with pd.ExcelWriter(file_path, engine='xlsxwriter',
# options={'strings_to_urls': False}) as writer:
baseCore.writerToExcel(all, file_path)
# combined_data.to_excel(writer, index=False)
# 该公众号的所有文章采集完成
# print(f'{fakeid}:采集成功！')
log.info(f'{fakeid}、公众号{origin}:采集成功！、已采集{count}个公众号')
else:
log.info(f'{fakeid}、公众号{origin}:{url_news},{news_title}已采集过该文章！、已采集{count}个公众号')
except:
# json解析该公众号成功但采集数据失败
count += 1
log.info(f'{fakeid}、公众号：{origin}采集失败！！！！！！已采集{count}个公众号')
# print(f'{fakeid}:解析失败！！！！！！')
list_error_url.append(str_t)
get_error_origin.append(origin)
get_error_code.append(info_source_code)
excel_name = time.strftime("%Y-%m-%d", time.localtime())
df_error_url = pd.DataFrame({'公众号：': get_error_origin,
'code': get_error_code,
'信息': list_error_url})
file_path = f'./保存失败/{excel_name}.xlsx'
if os.path.exists(file_path):
pass
else:
workbook = Workbook()
workbook.save(file_path)
workbook.close()
# df_error_url.to_excel(f'./保存失败/{excel_name}.xlsx', index=False)
# with pd.ExcelWriter(file_path,engine='xlsxwriter',options={'strings_to_urls':False}) as writer:
baseCore.writerToExcel(df_error_url, file_path)
# combined_data.to_excel(writer,index=False)
time.sleep(1)
continue
elif ret == 200002:
# 公众号链接错误 保存库里 记录错误信息及错误类型
time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
error = [
origin,
url_,
info_source_code,
str_t,
'无效biz参数',
time_now
]
insertSql = f"insert into WeixinGZH (site_name,site_url,info_source_code,json_error_info,error_type,create_time) values (%s,%s,%s,%s,%s,%s)"
cursor_.execute(insertSql, tuple(error))
cnx_.commit()
log.info(f'公众号----{origin}----耗时{baseCore.getTimeCost(start_,time.time())}')
continue
elif ret == 200003:
# 无效的session
time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
error = [
origin,
url_,
info_source_code,
str_t,
'无效session',
time_now
]
insertSql = f"insert into WeixinGZH (site_name,site_url,info_source_code,json_error_info,error_type,create_time) values (%s,%s,%s,%s,%s,%s)"
cursor_.execute(insertSql, tuple(error))
cnx_.commit()
log.info(f'公众号----{origin}----耗时{baseCore.getTimeCost(start_, time.time())}')
continue
else:
log.info(f'----其他情况-----{json_search}---公众号{origin}------')
time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
error = [
origin,
url_,
info_source_code,
str_t,
'其他错误',
time_now
]
insertSql = f"insert into WeixinGZH (site_name,site_url,info_source_code,json_error_info,error_type,create_time) values (%s,%s,%s,%s,%s,%s)"
cursor_.execute(insertSql, tuple(error))
cnx_.commit()
continue
else:
# list_all为空
list_all = json_search['app_msg_list']
try:
list_all_info,num_caiji= get_info(sid,json_search)
time.sleep(2)
if len(list_all_info) != 0:
count += 1
time_end = time.strftime("%Y-%m-%d_%H-%M-%S", time.localtime())
# print(f'{fakeid}:运行出错！时间为：{time_end}')
log.info(f'{fakeid}、公众号{origin}:list_all为空！已采集{count}个公众号、时间为：{time_end}')
json_error_biz.append(fakeid)
json_error_origin.append(origin)
json_error_code.append(info_source_code)
df_error_json = pd.DataFrame({'公众号：': json_error_origin,
'code': json_error_code,
'信息': json_error_biz})
file_path = f'./错误文件/{time_end}.xlsx'
if os.path.exists(file_path):
pass
else:
workbook = Workbook()
workbook.save(file_path)
workbook.close()
# df_error_json.to_excel(f'./错误文件/{time_end}.xlsx', index=False)
# with pd.ExcelWriter(file_path, engine='xlsxwriter',
# options={'strings_to_urls': False}) as writer:
baseCore.writerToExcel(df_error_json, file_path)
# combined_data.to_excel(writer, index=False)
time_end = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
log.info(f'运行结束，时间为：{time_end}')
print(f'运行结束，时间为：{time_end}')
df_info = pd.DataFrame(list_all_info)
excel_name = time.strftime("%Y-%m-%d", time.localtime())
df_info.to_excel(f'./运行结果/{excel_name}_总数据.xlsx', index=False)
list_b[0].refresh()
time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
success = [
origin,
url_,
info_source_code,
num_caiji,
'采集成功',
time_now
]
#成功信息保存
insertSql = f"insert into WeixinGZH (site_name,site_url,info_source_code,success_info,success_num,create_time) values (%s,%s,%s,%s,%s,%s)"
cursor_.execute(insertSql, tuple(success))
cnx_.commit()
# 该公众号的所有文章采集完成
log.info(f'{fakeid}、公众号{origin}:采集成功！、已采集{count}个公众号、耗时{baseCore.getTimeCost(start_,time.time())}')
else:
log.info(f'{fakeid}、公众号{origin}、网址已存在！耗时{baseCore.getTimeCost(start_,time.time())}')
except Exception as e:
# json解析该公众号成功但采集数据失败
count += 1
time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
false = [
origin,
url_,
info_source_code,
e,
'采集失败',
time_now
]
# 成功信息保存
insertSql = f"insert into WeixinGZH (site_name,site_url,info_source_code,json_error_info,error_type,create_time) values (%s,%s,%s,%s,%s,%s)"
cursor_.execute(insertSql, tuple(false))
cnx_.commit()
log.info(f'{fakeid}、公众号：{origin}采集失败！！！！！！耗时{baseCore.getTimeCost(start_, time.time())}')
time.sleep(2)
#关闭资源
cnx.close()
cursor.close()
baseCore.close()
comData/weixin_solo/test.py
import pandas as pd
def writeaa():
detailList=[]
aa={
'id':3,
'name':'qqqwe'
}
detailList.append(aa)
writerToExcel(detailList)
# def writeaa():
# detailList=[]
# aa={
# 'id':3,
# 'name':'qqqwe'
# }
# detailList.append(aa)
# writerToExcel(detailList)
# 将数据追加到excel
def writerToExcel(detailList):
# filename='baidu搜索.xlsx'
# 读取已存在的xlsx文件
existing_data = pd.read_excel(filename,engine='openpyxl')
# 创建新的数据
new_data = pd.DataFrame(data=detailList)
# 将新数据添加到现有数据的末尾
combined_data = existing_data.append(new_data, ignore_index=True)
# 将结果写入到xlsx文件
combined_data.to_excel(filename, index=False)
# def writerToExcel(detailList):
# # filename='baidu搜索.xlsx'
# # 读取已存在的xlsx文件
# existing_data = pd.read_excel(filename,engine='openpyxl')
# # 创建新的数据
# new_data = pd.DataFrame(data=detailList)
# # 将新数据添加到现有数据的末尾
# combined_data = existing_data.append(new_data, ignore_index=True)
# # 将结果写入到xlsx文件
# combined_data.to_excel(filename, index=False)
#
# from openpyxl import Workbook
#
# if __name__ == '__main__':
# filename='test1.xlsx'
# # # 创建一个工作簿
# workbook = Workbook(filename)
# workbook.save(filename)
# writeaa()
from openpyxl import Workbook
if __name__ == '__main__':
filename='test1.xlsx'
# # 创建一个工作簿
workbook = Workbook(filename)
workbook.save(filename)
writeaa()
gpdm = '01109.HK'
if 'HK' in str(gpdm):
tmp_g = str(gpdm).split('.')[0]
if len(tmp_g) == 5:
gpdm = str(gpdm)[1:]
print(gpdm)
else:
pass
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论