108 lines
3.8 KiB
Python
108 lines
3.8 KiB
Python
import pandas as pd
|
|
import os
|
|
import html2text
|
|
|
|
current_dir = os.getcwd()
|
|
wechat_dir = os.path.join(current_dir, 'wechat_dir')
|
|
web_dir = os.path.join(current_dir, 'web_dir')
|
|
output_dir = os.path.join(current_dir, 'summary')
|
|
df_s = pd.read_excel('biao.xlsx', sheet_name='筛查内容')
|
|
|
|
def trans_to_json():
|
|
json_str = df_s.to_json(orient='records', force_ascii=False)
|
|
with open('biao.json', 'w', encoding='utf-8') as f:
|
|
f.write(json_str)
|
|
|
|
def make_wechat_articles_full():
|
|
df = pd.read_excel(os.path.join(wechat_dir, 'articles.xlsx'))
|
|
df['content'] = ''
|
|
for ind, row in df.iterrows():
|
|
full_path = os.path.join(wechat_dir, row['nickname'], row['id'] + '.html')
|
|
try:
|
|
with open(full_path, encoding='utf-8') as f:
|
|
h = html2text.HTML2Text()
|
|
h.ignore_links = True
|
|
df.at[ind, 'content'] = h.handle(f.read())
|
|
print(f'{ind}--{row["nickname"]}--{row["title"]}')
|
|
except:
|
|
print(full_path + '---不存在')
|
|
output_path = os.path.join(wechat_dir, 'articles_full.csv')
|
|
df.to_csv(output_path, encoding='utf-8_sig')
|
|
|
|
def ana_wechat():
|
|
articles_full_path = os.path.join(wechat_dir, 'articles_full.csv')
|
|
if not os.path.exists(articles_full_path):
|
|
make_wechat_articles_full()
|
|
|
|
df = pd.read_csv(articles_full_path)
|
|
df['content'] = df['content'].fillna('')
|
|
|
|
output_data = []
|
|
index = 1
|
|
|
|
for ind, row in df_s.iterrows():
|
|
mask = df['content'].str.contains(row['错误表述'])
|
|
result = df[mask]
|
|
|
|
if not result.empty:
|
|
for ind2, row2 in result.iterrows():
|
|
output_row = [
|
|
index,
|
|
row2['nickname'],
|
|
row2['title'],
|
|
row['错误表述'],
|
|
row['建议修改词语'],
|
|
row['错误分类'],
|
|
row2['content_url']
|
|
]
|
|
output_data.append(output_row)
|
|
index += 1
|
|
|
|
output_data.insert(0, ['序号', '信源名称', '文章标题', '错误表述', '建议修改词语', '错误分类', '原文链接'])
|
|
|
|
return output_data
|
|
|
|
|
|
def ana_web():
|
|
output_data = []
|
|
index = 1
|
|
|
|
for file in os.listdir(web_dir):
|
|
full_path = os.path.join(web_dir, file)
|
|
if os.path.getsize(full_path) > 0:
|
|
df = pd.read_excel(os.path.join(web_dir, file))
|
|
for ind, row in df_s.iterrows():
|
|
mask = df['text'].str.contains(row['错误表述'], na=False)
|
|
result = df[mask]
|
|
if not result.empty:
|
|
for ind2, row2 in result.iterrows():
|
|
output_row = [
|
|
index,
|
|
row2['name'],
|
|
"文章标题",
|
|
row['错误表述'],
|
|
row['建议修改词语'],
|
|
row['错误分类'],
|
|
row2['content_url']
|
|
]
|
|
output_data.append(output_row)
|
|
index += 1
|
|
|
|
output_data.insert(0, ['序号', '信源名称', '文章标题', '错误表述', '建议修改词语', '错误分类', '原文链接'])
|
|
|
|
return output_data
|
|
|
|
# Run WeChat Analysis
|
|
wechat_results = ana_wechat()
|
|
|
|
# Run Web Content Analysis
|
|
web_results = ana_web()
|
|
|
|
# Save results in an Excel file with two sheets
|
|
output_excel_path = os.path.join(output_dir, '总院及下属公司官方公众号巡查结果汇总表.xlsx')
|
|
with pd.ExcelWriter(output_excel_path) as writer:
|
|
wechat_results.to_excel(writer, sheet_name='公众号', index=False)
|
|
web_results.to_excel(writer, sheet_name='网站', index=False)
|
|
|
|
print("Analysis completed and results saved to Excel.")
|