Created
March 12, 2018 19:52
-
-
Save vural/3c5065cf0e20871501b0bada2967f19a to your computer and use it in GitHub Desktop.
megep
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
from bs4 import BeautifulSoup | |
class Parser(object): | |
__slots__ = ('_view_state', '_view_state_generator') | |
def __init__(self): | |
main_page_resp = requests.get('http://megep.meb.gov.tr/?page=moduller').text | |
soup = BeautifulSoup(main_page_resp, 'html.parser') | |
self._view_state = soup.find(id="__VIEWSTATE").get('value') | |
self._view_state_generator = soup.find(id="__VIEWSTATEGENERATOR").get('value') | |
def parse_category(self): | |
category_params = ( | |
('tip', 'modulAlanDoldur'), | |
('id', '0'), | |
) | |
resp_category = requests.get('http://megep.meb.gov.tr/JSON.aspx', params=category_params).json() | |
return resp_category['Head'] | |
def parse_item(self, id): | |
detail_params = ( | |
('tip', 'alanChange'), | |
('id', id), | |
) | |
resp = requests.get('http://megep.meb.gov.tr/JSON.aspx', params=detail_params).json() | |
return resp['Head'] | |
def parse_document(self, category_id, sub_category_id): | |
headers = { | |
'Origin': 'http://megep.meb.gov.tr', | |
'Accept-Encoding': 'gzip, deflate', | |
'Accept-Language': 'tr,en-US;q=0.9,en;q=0.8', | |
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36', | |
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', | |
'Accept': '*/*', | |
'Cache-Control': 'no-cache', | |
'X-Requested-With': 'XMLHttpRequest', | |
'Connection': 'keep-alive', | |
'X-MicrosoftAjax': 'Delta=true', | |
'Referer': 'http://megep.meb.gov.tr/?page=moduller', | |
} | |
data = [ | |
('ScriptManager1', 'ScriptManager1|ctl10$drpDersListe'), | |
('__EVENTTARGET', 'ctl10$drpDersListe'), | |
('__EVENTARGUMENT', ''), | |
('__LASTFOCUS', ''), | |
('__VIEWSTATE', self._view_state), | |
('__VIEWSTATEGENERATOR', self._view_state_generator), | |
('ctl10$drpModulAlanListe', category_id), | |
('ctl10$hdnAlanId', category_id), | |
('ctl10$drpDersListe', sub_category_id), | |
('ctl10$hdnDersId', sub_category_id), | |
('ctl10$txtModulAd', ''), | |
('ctl10$txtModulKod', ''), | |
('ctl10$drpModulAlanListe_2015', ''), | |
('ctl10$hdnAlanId_2015', ''), | |
('ctl10$drpDersListe_2015', ''), | |
('ctl10$hdnDersId_2015', '0'), | |
('__ASYNCPOST', 'true'), | |
('', ''), | |
] | |
docs_resp = requests.post('http://megep.meb.gov.tr/', headers=headers, params={'page':'moduller'}, data=data) | |
soup = BeautifulSoup(docs_resp.text, 'html.parser') | |
for link in soup.find_all('a'): | |
yield 'http://megep.meb.gov.tr/{}'.format(link.get("href")) | |
def parse(self): | |
for category in self.parse_category(): | |
category_id, category_name = category['ID'], category['alanAd'] | |
for item in self.parse_item(category_id): | |
item_id, item_name = item['ID'], item['dersAd'] | |
for document in self.parse_document(category_id, item_id): | |
yield { | |
'main_category_name': category_name, | |
'sub_category_name': item_name, | |
'document': document | |
} | |
parser = Parser() | |
for i in parser.parse(): | |
print(i) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment