zcdsj
/
zcspider
5
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: 总院官网连不上的异常处理

This commit is contained in:
caoqianming 2025-06-18 14:58:13 +08:00
parent 5553965ddb
commit 975596f0b0
1 changed files with 20 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
mycode/main.py
View File

@ -150,6 +150,7 @@ def get_cbma_info_from_db_and_ana(year: str = '2023'):
df_web = pd.read_sql_query(query_web, conn_web)
conn_web.close()
except Exception as e:
df_web = None
print(e)
df['source'] = ''
@ -195,12 +196,12 @@ def get_cbma_info_from_db_and_ana(year: str = '2023'):
# df_fx.at[ind, '供总院全年稿数'] = ((df['source'].str.contains(dw))&(df['gbiz']==zybiz)).sum()
df_fx.at[ind, '供总院全年专稿数'] = (
(df['source'] == dw) & (df['gbiz'] == zybiz)).sum()
df_fx.at[ind, '供总院网站全年专稿数'] = (
(df_web['source'] == dw)).sum()
df_fx.at[ind, '供总院全年组稿数'] = ((df['source'].str.contains(
dw) & (df['source'] != dw)) & (df['gbiz'] == zybiz)).sum()
df_fx.at[ind, '供总院网站全年专稿数'] = (
(df_web['source'] == dw)).sum() if df_web is not None else 0
df_fx.at[ind, '供总院全年网站组稿数'] = ((df_web['source'].str.contains(
dw) & (df_web['source'] != dw))).sum()
dw) & (df_web['source'] != dw))).sum() if df_web is not None else 0
df_fx.at[ind, '供总院全年阅读10000及以上数'] = ((df['read_num'] >= 10000) & (
df['source'].str.contains(dw)) & (df['gbiz'] == zybiz)).sum()
df_fx.at[ind, '供总院全年阅读5000及以上数'] = ((df['read_num'] >= 5000) & (
@ -212,26 +213,26 @@ def get_cbma_info_from_db_and_ana(year: str = '2023'):
if '月' in i:
i_str = i.replace('月', '').zfill(2)
cons_y_m = (df['pub_month'] == str(i_str))
cons_y_m_web = (df_web['pub_month'] == str(i_str))
cons_y_m_web = (df_web['pub_month'] == str(i_str)) if df_web is not None else pd.Series(False)
elif i == '上半年':
cons_y_m = (df['pub_month'] == '01') | (df['pub_month'] == '02') | (df['pub_month'] == '03') | (
df['pub_month'] == '04') | (df['pub_month'] == '05') | (df['pub_month'] == '06')
cons_y_m_web = (df_web['pub_month'] == '01') | (df_web['pub_month'] == '02') | (df_web['pub_month'] == '03') | (
df_web['pub_month'] == '04') | (df_web['pub_month'] == '05') | (df_web['pub_month'] == '06')
df_web['pub_month'] == '04') | (df_web['pub_month'] == '05') | (df_web['pub_month'] == '06') if df_web is not None else pd.Series(False)
elif i == '下半年':
cons_y_m = (df['pub_month'] == '07') | (df['pub_month'] == '08') | (df['pub_month'] == '09') | (
df['pub_month'] == '10') | (df['pub_month'] == '11') | (df['pub_month'] == '12')
cons_y_m_web = (df_web['pub_month'] == '07') | (df_web['pub_month'] == '08') | (df_web['pub_month'] == '09') | (
df_web['pub_month'] == '10') | (df_web['pub_month'] == '11') | (df_web['pub_month'] == '12')
df_web['pub_month'] == '10') | (df_web['pub_month'] == '11') | (df_web['pub_month'] == '12') if df_web is not None else pd.Series(False)
elif i == '全年':
cons_y_m = pd.Series(True, index=df.index)
cons_y_m_web = pd.Series(True, index=df_web.index)
cons_y_m_web = pd.Series(True, index=df_web.index) if df_web is not None else pd.Series(False)
if '、' in dw: # 针对这种同一部门的
cons_dw_1 = pd.Series(False, index=df.index)
cons_dw_1_web = pd.Series(False, index=df_web.index)
cons_dw_1_web = pd.Series(False, index=df_web.index) if df_web is not None else pd.Series(False)
for item in dw.split('、'):
cons_dw_1 = (df['source'].str.contains(item)) | cons_dw_1
cons_dw_1_web = (df_web['source'].str.contains(item)) | cons_dw_1_web
cons_dw_1_web = (df_web['source'].str.contains(item)) | cons_dw_1_web if df_web is not None else (df_web['source'].str.contains(item))
df_fx.at[ind, f'供总院{i}稿数'] = ((cons_dw_1) & (
cons_y_m) & (df['gbiz'] == zybiz)).sum()
df_fx.at[ind, f'供总院网站{i}稿数'] = ((cons_dw_1_web) & (
@ -240,7 +241,7 @@ def get_cbma_info_from_db_and_ana(year: str = '2023'):
df_fx.at[ind, f'供总院{i}稿数'] = (df['source'].str.contains(
dw) & (cons_y_m) & (df['gbiz'] == zybiz)).sum()
df_fx.at[ind, f'供总院网站{i}稿数'] = (df_web['source'].str.contains(
dw) & (cons_y_m_web)).sum()
dw) & (cons_y_m_web)).sum() if df_web is not None else 0
df_fx[f'供总院{i}稿数'] = df_fx[f'供总院{i}稿数'].fillna(0)
df_fx[f'供总院{i}稿数'] = df_fx[f'供总院{i}稿数'].astype(int)
df_fx[f'供总院网站{i}稿数'] = df_fx[f'供总院网站{i}稿数'].fillna(0)
@ -261,7 +262,7 @@ def get_cbma_info_from_db_and_ana(year: str = '2023'):
max_read_row['read_num']), f'{max_read_row["pub_year"]}-{max_read_row["pub_month"]}-{max_read_row["pub_day"]}', max_read_row['source']]
df_fx.at[ind, f'{i}最高点击文章'] = '***'.join(max_read_row_list)
df_fx.at[ind, f'总院网站{i}发布数'] = cons_y_m_web.sum()
df_fx.at[ind, f'总院网站{i}发布数'] = cons_y_m_web.sum() if df_web is not None else 0
df_fx[f'总院网站{i}发布数'] = df_fx[f'总院网站{i}发布数'].fillna(0)
df_fx[f'总院网站{i}发布数'] = df_fx[f'总院网站{i}发布数'].astype(int)
@ -291,13 +292,14 @@ def get_cbma_info_from_db_and_ana(year: str = '2023'):
sheet_web = workbook['官方网站更新数']
sheet_web.cell(row=1, column=1, value=f'关于{year}年度中国建材总院新媒体更新情况明细表\n（网站）')
ind_zyweb = 0
for ind, row in df_web.iterrows():
sheet_web.cell(row=ind_zyweb+3, column=1, value=str(ind_zyweb+1))
sheet_web.cell(row=ind_zyweb+3, column=2, value=f'{row["pub_year"]}-{row["pub_month"]}-{row["pub_day"]}')
sheet_web.cell(row=ind_zyweb+3, column=3, value=row['title'])
sheet_web.cell(row=ind_zyweb+3, column=4, value=row['source'])
sheet_web.cell(row=ind_zyweb+3, column=5, value=row['bankuai'])
ind_zyweb = ind_zyweb + 1
if df_web:
for ind, row in df_web.iterrows():
sheet_web.cell(row=ind_zyweb+3, column=1, value=str(ind_zyweb+1))
sheet_web.cell(row=ind_zyweb+3, column=2, value=f'{row["pub_year"]}-{row["pub_month"]}-{row["pub_day"]}')
sheet_web.cell(row=ind_zyweb+3, column=3, value=row['title'])
sheet_web.cell(row=ind_zyweb+3, column=4, value=row['source'])
sheet_web.cell(row=ind_zyweb+3, column=5, value=row['bankuai'])
ind_zyweb = ind_zyweb + 1
cbma_path = os.path.join(BASE_DIR, f'summary/{year}年_总院文章.xlsx')
workbook.save(cbma_path)
print(f'总院{year}年文章表生成完毕!')