def get_52_week_high_html(): #52 week high html url = 'http://www.bseindia.com/markets/equity/EQReports/HighLow.aspx?expandable=2' high_html = None while high_html is None: high_html = get_post_services.get_html_data(url) return high_html
def get_52_week_high_html(): # 52 week high html url = "http://www.bseindia.com/markets/equity/EQReports/HighLow.aspx?expandable=2" high_html = None while high_html is None: high_html = get_post_services.get_html_data(url) return high_html
def get_requester_url(i_security_code): url = "http://www.bseindia.com/SiteCache/1D/GetQuoteData.aspx" data = {"Type": "EQ", "text": i_security_code} html = get_post_services.get_html_data(url, params=data) while html is None: html = get_post_services.get_html_data(url, params=data) soup = BeautifulSoup(html, "lxml") tag = soup.find("a") if tag is None: data["Type"] = "MF" html = get_post_services.get_html_data(url, params=data) while html is None: html = get_post_services.get_html_data(url, params=data) soup = BeautifulSoup(html, "lxml") tag = soup.find("a") return tag["href"]
def get_requester_url(i_security_code): url = 'http://www.bseindia.com/SiteCache/1D/GetQuoteData.aspx' data = {'Type': 'EQ', 'text': i_security_code} html = get_post_services.get_html_data(url, params=data) while html is None: html = get_post_services.get_html_data(url, params=data) soup = BeautifulSoup(html, 'lxml') tag = soup.find('a') if tag is None: data['Type'] = 'MF' html = get_post_services.get_html_data(url, params=data) while html is None: html = get_post_services.get_html_data(url, params=data) soup = BeautifulSoup(html, 'lxml') tag = soup.find('a') return tag['href']
def get_ratios(ratio_urls): ratios = {} for url in ratio_urls: html_for_ratios = gps.get_html_data(url) if html_for_ratios is None: continue parsers = ['html.parser', 'lxml', 'html5lib'] for parser in parsers: ratios = parse_the_ratios_page(html_for_ratios, parser) if ratios is not None: break return ratios
def get_market_cap_and_name(i_security_code): url = "http://www.bseindia.com/stock-share-price/SiteCache/Stock_Trading.aspx" data = {"Type": "EQ", "text": i_security_code} headers = { "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:41.0) Gecko/20100101 Firefox/41.0", "Accept": "text/html, */*; q=0.01", "X-Requested-With": "XMLHttpRequest", "Referer": "", } headers["Referer"] = get_requester_url(i_security_code) html = get_post_services.get_html_data(url, params=data, headers=headers) while html is None: html = get_post_services.get_html_data(url, params=data, headers=headers) soup = BeautifulSoup(html, "lxml") return [ i_security_code, soup.find(id="ehd6")["value"].replace(",", "").replace("-", "0"), headers["Referer"].split("/")[4], ]
def get_market_cap_and_name(i_security_code): url = 'http://www.bseindia.com/stock-share-price/SiteCache/Stock_Trading.aspx' data = {'Type': 'EQ', 'text': i_security_code} headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:41.0) Gecko/20100101 Firefox/41.0', 'Accept': 'text/html, */*; q=0.01', 'X-Requested-With': 'XMLHttpRequest', 'Referer': '' } headers['Referer'] = get_requester_url(i_security_code) html = get_post_services.get_html_data(url, params=data, headers=headers) while html is None: html = get_post_services.get_html_data(url, params=data, headers=headers) soup = BeautifulSoup(html, 'lxml') return [ i_security_code, soup.find(id='ehd6')['value'].replace(',', '').replace('-', '0'), headers['Referer'].split('/')[4] ]
def get_company_names_for_url(search_keywords): url = 'http://www.moneycontrol.com/stocks/cptmarket/compsearchnew.php' data = { 'search_data' : '', 'cid' : '', 'mbsearch_str' : '', 'topsearch_type' : '1', 'search_str': '' } for keyword in search_keywords: data['search_str'] = keyword html = gps.get_html_data(url, params=data) soup = BeautifulSoup(html, 'lxml') standalone = soup.find(attrs={'class':'home act'}) if standalone is not None: break if standalone is None: return None return standalone
def get_company_names_for_url(search_keywords): url = 'http://www.moneycontrol.com/stocks/cptmarket/compsearchnew.php' data = { 'search_data': '', 'cid': '', 'mbsearch_str': '', 'topsearch_type': '1', 'search_str': '' } for keyword in search_keywords: data['search_str'] = keyword html = gps.get_html_data(url, params=data) soup = BeautifulSoup(html, 'lxml') standalone = soup.find(attrs={'class': 'home act'}) if standalone is not None: break if standalone is None: return None return standalone