def get_sub_content(link, f:'_io.TextIOWrapper'):
#print("http://"+baseurl[0:-1]+link)
(req, ans) = get_content("http://"+baseurl+link)
soup=BeautifulSoup(ans,from_encoding="utf-8")
content = soup.find(class_='CardView')
content = content.find_all('table')
result = ''
for table in content[0:2]:
for td in table.find_all('td')[1::2]:
result+=td.get_text()+';'
result += content[2].find_all('td')[4].get_text()+';'
result = result.replace('\t', '').replace('\n', '').replace('\x0D', '')
result = normalUtf(result)
f.write(result+'\n')
f.flush()
def inf_from_table(table:'BeautifulSoup',f:'_io.TextIOWrapper'):
rows=table.find_all('tr',class_='RowsTable_Default')
rows2=table.find_all('tr',class_='RowsTable_Default_')
rows=rows+rows2
for row in rows:
str=''
row_data=row.find_all('td')
#<notice_number>
str=str+row_data[1].get_text()+';'
#</notice_number>
#<subject>
str=str+row_data[2].get_text()+';'
#</subject>
#<price>
str=str+row_data[3].get_text()+';'
#</price>
#<organizer>
str=str+row_data[4].get_text()+';'
#</organizer>
#<publication_date_time>
str=str+row_data[5].get_text()+';'
#</publication_date_time>
#<start_date>
str=str+row_data[6].get_text()+';'
#</start_date>
#<start_time>
str=str+row_data[7].get_text()+';'
#</start_time>
#<state>
str=str+row_data[8].get_text()+';'
#</state>
#<url>
link = row_data[0].find('a');
if not (link is None):
#print(link['href'])
str=str+link['href'].replace('\n', '')+';'
#</url>
str=normalUtf(str)
f.write(str)
f.flush()
#begin full info about zakaz
get_sub_content(link['href'], f)
#end full info about zakaz
return link['href']
main_table=soup.find("table",class_="tbl_org tbl_org_zakon tbl_org_regedit tbl_torgs ")
lines=main_table.find_all("tr")
g=1
num_ln=len(lines)
while g < num_ln:
_str='';
cur_line=lines[g]
#begin get information about competition
link = cur_line['onclick']
url_with_full_inf = link.split("'")[1]
_str+=subInfo(url_with_full_inf)
#end get information about competition
data_in_line=cur_line.find_all("td")
#<customer>
_str=_str+data_in_line[0].get_text()+';'
#</customer>
#<subject>
_str=_str+data_in_line[1].get_text()+';'
#</subject>
#<date>
_str=_str+data_in_line[2].get_text()+';'
#</date>
g=g+1
_str = normalUtf(_str)
inf_file.write(_str)
inf_file.write("\n")
inf_file.flush()
cur_page=cur_page+1
inf_file.close()