def dataProcess_Detail(soup):
result = dict()
# 主旨
result['title'] = [e.text for e in soup.select("h3")][1]
# 內容
result['content'] = [
header.spaceAndWrapProcess(e.text)
for e in soup.select('.page_content')
][0]
# 附件
result['FILES'] = [
e.get("title").replace("(開啟新視窗)", "") for e in soup.select('.acces a')
]
FILES_NM = [
os.path.splitext(ele)[0][:30] + os.path.splitext(ele)[1]
for ele in result['FILES']
]
result['FILES_NM'] = header.processDuplicateFiles(FILES_NM)
logging.info(result['FILES_NM'])
result['fileUrls'] = [
"https://www.ib.gov.tw" + e.get('href')
for e in soup.select('.acces a')
]
str_content = str(soup.select('.page_content')[0])
result['serno'] = getResult(re.findall(r'發文字號.+?\d+.+?', str_content), 5)
result['issue_date'] = getResult(re.findall(r'發文日期.+?日', str_content), 5)
return result
def dataProcess_Detail(soup, title_type):
result = dict()
fileUrlRoot = 'http://law.tii.org.tw/Fn/'
str_content = [e.text for e in soup.select('pre')][0]
if title_type == '行政函釋':
contentlist = re.findall('主 旨：.+',
header.spaceAndWrapProcess(str_content))
if bool(contentlist):
content = contentlist[0]
else:
content = re.findall('一、.+',
header.spaceAndWrapProcess(str_content))[0]
serno = re.findall(r'發文字號.+?\d+.+', str_content)[0][5:-1]
issue_date = re.findall(r'發文日期.+?\d+.+', str_content)[0][5:-1]
else:
content = header.spaceAndWrapProcess(str_content)
content1 = re.sub('\s', '', str_content)
serno = re.findall('日\S+?號[令|函|(公告)]', content1)[0][1:]
issue_date = re.findall('民國.+?日', str_content)[0]
result['FILES'] = [e.text for e in soup.select('font font a')]
FILES_NM = [
os.path.splitext(ele)[0][:30] + os.path.splitext(ele)[1]
for ele in result['FILES']
]
result['FILES_NM'] = header.processDuplicateFiles(FILES_NM)
logging.info(result['FILES_NM'])
result['fileUrls'] = [
re.sub(r'\.\/', fileUrlRoot, e.get('href'))
for e in soup.select('font font a')
]
result['content'] = content
result['serno'] = serno
result['issue_date'] = issue_date
return result
def dataProcess_Detail(soup, fileUrlRoot):
result = dict()
result['content'] = [header.spaceAndWrapProcess(e.text) for e in soup.select('.page_content')][0]
result['FILES'] = [e.text for e in soup.select('.acces a')]
FILES_NM = [os.path.splitext(ele)[0][:30] + os.path.splitext(ele)[1] for ele in result['FILES']]
result['FILES_NM'] = header.processDuplicateFiles(FILES_NM)
#logging.info(result['FILES_NM'])
result['fileUrls'] = [fileUrlRoot + e.get('href') for e in soup.select('.acces a')]
str_content = str(soup.select('.page_content')[0])
result['serno'] = re.findall(r'發文字號.+?\d+.+?', str_content)[0][5:]
result['issue_date'] = re.findall(r'發文日期.+?日', str_content)[0][5:]
return result
def dataProcess_Detail(soup, row):
urlGazette = 'https://gazette.nat.gov.tw' # linkto 行政院公報資訊網
urlGazette1 = 'http://gazette.nat.gov.tw' # linkto 行政院公報資訊網
urlmoj = 'https://law.moj.gov.tw/News/' # linkto 全國法規資料庫
urlfsc = 'http://law.fsc.gov.tw/law/' # linkto 主管法規查詢系統
title = row['TITL']
link = row['LNK_URL']
result = dict()
if link.find(urlGazette) >= 0 or link.find(urlGazette1) >= 0:
fileUrls = [urlGazette + e.get('src') for e in soup.select('.embed-responsive-item')]
fileNames = [title + '.pdf' for i in range(len(fileUrls))]
content = ''
serno = [e.text for e in soup.select('section.Block p span')][2]
issue_date = soup.select('div.Item section.Block p span')[1].text
elif link.find(urlmoj) >= 0:
content = [header.spaceAndWrapProcess(e.text) for e in soup.select('.text-pre')][0]
fileNames = [e.text for e in soup.select('#litFile a')]
fileUrls = [urlmoj + '/' + e.get('href') for e in soup.select('#Content a')]
serno = ''
issue_date = [e.text for e in soup.select('td')][0]
elif link.find(urlfsc) >= 0:
if link.find('DraftOpinion.aspx') >= 0:
content = '預告日期：' + [e.text.strip() for e in soup.select('td')][1]
serno = [e.text.strip() for e in soup.select('td')][2]
issue_date = [e.text.strip() for e in soup.select('td')][0][:9]
elif link.find('NewsContent.aspx') >= 0:
content1 = [header.spaceAndWrapProcess(e.text) for e in soup.select('.ClearCss')]
content2 = [header.spaceAndWrapProcess(e.text) for e in soup.select('#ctl00_cp_content_trPreamble td')]
content = content1[0] if content1 else content2[0]
serno = [e.text.strip() for e in soup.select('#ctl00_cp_content_trODWord td')][0]
issue_date = [e.text.strip() for e in soup.select('#ctl00_cp_content_trAnnDate td')][0]
fileUrls = [urlfsc + e.get('href') for e in soup.select('#ctl00_cp_content_ulAnnFiles02 a')]
fileNames = [e.text for e in soup.select('#ctl00_cp_content_ulAnnFiles02 a')]
result['fileUrls'] = fileUrls
result['FILES'] = fileNames
FILES_NM = [os.path.splitext(ele)[0][:30] + os.path.splitext(ele)[1] for ele in result['FILES']]
result['FILES_NM'] = header.processDuplicateFiles(FILES_NM)
result['content'] = content
result['serno'] = serno
result['issue_date'] = issue_date
return result