AI_Video_LP/python_utils/gen_daily_report.py

#!/usr/bin/python3

from pytrends.request import TrendReq
import pytrends
import sys
from datetime import datetime, timezone, timedelta
import traceback
import requests
from bs4 import BeautifulSoup
import re
#import farmlib
import pandas as pd
import random
import os
import dataset
import json
from gn3 import GoogleNews3

googlenews = GoogleNews3(lang="zh-tw", period="7d",
                         encode="utf-8", region="tw")

# googlenews.search('蔡英文')

""" result = googlenews.gettext()

for n in range(len(result)):
    print(n)
    print(result[n])

result = googlenews.get_links()

for n in range(len(result)):
    print(n)
    print(result[n]) """

""" googlenews.get_news('蔡英文')
trdresult = googlenews.result()

#print(trdresult[0]['title'])
for article in trdresult:
    print(article['title']) """

db = dataset.connect(
    'mysql://choozmo:pAssw0rd@db.ptt.cx:3306/yodb?charset=utf8mb4')
cursor = db.query(
    '(SELECT * FROM trending_searches ORDER BY ts_date DESC LIMIT 20) ORDER BY ts_date')

""" for c in cursor:
    print(c['ts_word']) """

tz = timezone(timedelta(hours=+8))
#print(datetime.now(tz).isoformat(timespec="seconds"))
# print(str(datetime.date.today()).replace('-',''))

trpath = os.getcwd() + '/../webSite/content/trends/'
trdpath = os.getcwd() + '/../webSite/content/trenddetail/'
with open(trpath + str(datetime.today().date()).replace('-', '')+'.md', 'w', encoding='UTF-8') as f:
    f.write('+++\n')
    f.write('title = "趨勢日報"\n' +
            'date = "' + str(datetime.now(tz).isoformat(timespec="seconds")) + '"\n' +
            'tags = ["daily-trend-watch"]\n' +
            'categories = ["trends"]\n' +
            'layout = "trends"\n' +
            'banner = "https://i.imgur.com/jdQb3ZH.jpg"\n')
    for c in cursor:
        f.write('no' + str(c['ts_rank']).zfill(2) +
                ' = "' + c['ts_word'] + '"\n')
        googlenews.clear()
        googlenews.get_news(c['ts_word'])
        trdresult = googlenews.result()
        with open(trdpath + str(datetime.today().date()).replace('-', '')+'_' + str(c['ts_rank']).zfill(2)+'.md', 'w', encoding='UTF-8') as fd:
            fd.write('+++\n')
            fd.write('title = "趨勢日報"\n' +
                     'date = "' + str(datetime.now(tz).isoformat(timespec="seconds")) + '"\n' +
                     'layout = "trends"\n' +
                     'banner = "https://i.imgur.com/jdQb3ZH.jpg"\n')
            rcount = 1
            print(c['ts_word'])
            for article in trdresult:
                fd.write('title' + str(rcount)+' = "' + str(article['title']).replace('"',"'") + '"\n' +
                         'desc' + str(rcount)+' = "' + str(article['desc']) + '"\n' +
                         'date' + str(rcount)+' = "' + str(article['date']) + '"\n' +
                         'datetime' + str(rcount)+' = "' + str(article['datetime']) + '"\n' +
                         'link' + str(rcount)+' = "' + str(article['link']) + '"\n' +
                         'img' + str(rcount)+' = "' + str(article['img']) + '"\n' +
                         'media' + str(rcount)+' = "' + str(article['media']) + '"\n' +
                         'site' + str(rcount)+' = "' + str(article['site']) + '"\n')
                # print(article)
                rcount += 1
            fd.write('+++\n')
    f.write('+++\n')