我们从Python开源项目中,提取了以下50个代码示例,用于说明如何使用urlparse.urljoin()。
def call_api(self, method, endpoint, payload): url = urlparse.urljoin(self.api_base_url, endpoint) if method == 'POST': response = requests.post(url, data=payload) elif method == 'delete': response = requests.delete(url) elif method == 'put': response = requests.put(url, data=payload) else: if self.api_key: payload.update({'api_token': self.api_key}) response = requests.get(url, params=payload) content = json.loads(response.content) return content
def redirect_internal(self, url, fp, errcode, errmsg, headers, data): if 'location' in headers: newurl = headers['location'] elif 'uri' in headers: newurl = headers['uri'] else: return void = fp.read() fp.close() # In case the server sent a relative URL, join with original: newurl = basejoin(self.type + ":" + url, newurl) # For security reasons we do not allow redirects to protocols # other than HTTP, HTTPS or FTP. newurl_lower = newurl.lower() if not (newurl_lower.startswith('http://') or newurl_lower.startswith('https://') or newurl_lower.startswith('ftp://')): raise IOError('redirect error', errcode, errmsg + " - Redirection to url '%s' is not allowed" % newurl, headers) return self.open(newurl)
def get(self, netloc, ua, timeout): try: headers = {'User-Agent': ua, 'Referer': netloc} result = _basic_request(netloc, headers=headers, timeout=timeout) match = re.findall('xhr\.open\("GET","([^,]+),', result) if not match: return False url_Parts = match[0].split('"') url_Parts[1] = '1680' url = urlparse.urljoin(netloc, ''.join(url_Parts)) match = re.findall('rid=([0-9a-zA-Z]+)', url_Parts[0]) if not match: return False headers['Cookie'] = 'rcksid=%s' % match[0] result = _basic_request(url, headers=headers, timeout=timeout) return self.getCookieString(result, headers['Cookie']) except: return # not very robust but lazieness...
def movie(self, imdb, title, localtitle, aliases, year): try: t = 'http://www.imdb.com/title/%s' % imdb t = client.request(t, headers={'Accept-Language': 'es-AR'}) t = client.parseDOM(t, 'title')[0] t = re.sub('(?:\(|\s)\d{4}.+', '', t).strip().encode('utf-8') q = self.search_link % urllib.quote_plus(t) q = urlparse.urljoin(self.base_link, q) r = client.request(q) r = client.parseDOM(r, 'div', attrs = {'class': 'item'}) r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'span', attrs = {'class': 'tt'}), client.parseDOM(i, 'span', attrs = {'class': 'year'})) for i in r] r = [(i[0][0], i[1][0], i[2][0]) for i in r if len(i[0]) > 0 and len(i[1]) > 0 and len(i[2]) > 0] r = [i[0] for i in r if cleantitle.get(t) == cleantitle.get(i[1]) and year == i[2]][0] url = re.findall('(?://.+?|)(/.+)', r)[0] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: pass
def searchMovie(self, title, year, aliases, headers): try: title = cleantitle.normalize(title) url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(cleantitle.getsearch(title))) r = client.request(url, headers=headers, timeout='15') r = client.parseDOM(r, 'div', attrs={'class': 'ml-item'}) r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a', ret='title')) results = [(i[0], i[1], re.findall('\((\d{4})', i[1])) for i in r] try: r = [(i[0], i[1], i[2][0]) for i in results if len(i[2]) > 0] url = [i[0] for i in r if self.matchAlias(i[1], aliases) and (year == i[2])][0] except: url = None pass if (url == None): url = [i[0] for i in results if self.matchAlias(i[1], aliases)][0] return url except: return
def searchMovie(self, title, year, aliases, headers): try: title = cleantitle.normalize(title) url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(cleantitle.getsearch(title))) r = client.request(url, headers=headers, timeout='15') r = client.parseDOM(r, 'div', attrs={'class': 'item-detail'}) r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a', ret='title')) results = [(i[0], i[1], re.findall('\((\d{4})', i[1])) for i in r] try: r = [(i[0], i[1], i[2][0]) for i in results if len(i[2]) > 0] url = [i[0] for i in r if self.matchAlias(i[1], aliases) and (year == i[2])][0] except: url = None pass if (url == None): url = [i[0] for i in results if self.matchAlias(i[1], aliases)][0] url = '%s/watch' % url return url except: return
def movie(self, imdb, title, localtitle, aliases, year): try: t = cleantitle.get(title) p = self.post_link % urllib.quote_plus(cleantitle.query(title)) q = urlparse.urljoin(self.base_link, self.search_link) r = proxy.request(q, 'playing top', post=p, XHR=True) r = client.parseDOM(r, 'li') r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a')) for i in r] r = [(i[0][0], i[1][0]) for i in r if i[0] and i[1]] r = [(i[0], re.findall('(.+?)\((\d{4})', i[1])) for i in r] r = [(i[0], i[1][0][0], i[1][0][1]) for i in r if i[1]] r = [i for i in r if t == cleantitle.get(i[1]) and str(year) == i[2]] url = proxy.parse(r[0][0]) url = re.findall('(?://.+?|)(/.+)', url)[0] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: pass
def searchMovie(self, title, year, aliases, headers): try: title = cleantitle.normalize(title) url = urlparse.urljoin(self.base_link, self.search_link % cleantitle.geturl(title)) r = client.request(url, headers=headers, timeout='15') r = client.parseDOM(r, 'div', attrs={'class': 'ml-item'}) r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a', ret='title')) results = [(i[0], i[1], re.findall('\((\d{4})', i[1])) for i in r] try: r = [(i[0], i[1], i[2][0]) for i in results if len(i[2]) > 0] url = [i[0] for i in r if self.matchAlias(i[1], aliases) and (year == i[2])][0] except: url = None pass if (url == None): url = [i[0] for i in results if self.matchAlias(i[1], aliases)][0] url = '%s/watch' % url return url except: return
def searchMovie(self, title, year, aliases, headers): try: title = cleantitle.normalize(title) url = urlparse.urljoin(self.base_link, self.search_link % cleantitle.geturl(title)) r = client.request(url, headers=headers, timeout='15') r = client.parseDOM(r, 'div', attrs={'class': 'ml-item'}) r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a', ret='title')) results = [(i[0], i[1], re.findall('\((\d{4})', i[1])) for i in r] try: r = [(i[0], i[1], i[2][0]) for i in results if len(i[2]) > 0] url = [i[0] for i in r if self.matchAlias(i[1], aliases) and (year == i[2])][0] except: url = None pass if (url == None): url = [i[0] for i in results if self.matchAlias(i[1], aliases)][0] url = urlparse.urljoin(self.base_link, '%s/watching.html' % url) return url except: return
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) query = urlparse.urljoin(self.base_link, self.search_link) query = query % urllib.quote_plus(data['tvshowtitle']) t = cleantitle.get(data['tvshowtitle']) r = client.request(query) r = client.parseDOM(r, 'div', attrs = {'class': 'thumb'}) r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a', ret='title'), re.findall('(\d{4})', i)) for i in r] r = [(i[0][0], i[1][0], i[2][0]) for i in r if len(i[0]) > 0 and len(i[1]) > 0 and len(i[2]) > 0] url = [i[0] for i in r if t in cleantitle.get(i[1]) and ('Season %s' % season) in i[1]][0] url += '?episode=%01d' % int(episode) return url except: return
def movie(self, imdb, title, localtitle, aliases, year): try: query = self.search_mv_link % (urllib.quote_plus(title)) query = urlparse.urljoin(self.base_link, query) r = client.request(query, XHR=True) r = json.loads(r) t = cleantitle.get(title) r = [(i['slug'], i['title'], i['year']) for i in r] r = [i[0] for i in r if t == cleantitle.get(i[1]) and year == str(i[2])][0] url = r.encode('utf-8') return url except: return
def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year): try: query = self.search_tv_link % (urllib.quote_plus(tvshowtitle)) query = urlparse.urljoin(self.base_link, query) r = client.request(query, XHR=True) r = json.loads(r) t = cleantitle.get(tvshowtitle) r = [(i['slug'], i['title'], i['year']) for i in r] r = [i[0] for i in r if t == cleantitle.get(i[1]) and year == str(i[2])][0] url = r.encode('utf-8') return url except: return
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources url = self.movie_link % url url = urlparse.urljoin(self.base_link, url) return sources r = client.request(url) sources.append({'source': 'einthusan', 'quality': 'HD', 'language': 'en', 'url': url, 'direct': True, 'debridonly': False}) return sources except: return sources
def movie(self, imdb, title, localtitle, aliases, year): try: url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(title)) headers = {'Referer': url, 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.81 Safari/537.36'} cookie = client.request(url, headers=headers, output='cookie') cookie += client.request(url, headers=headers, cookie=cookie, output='cookie') client.request(url, headers=headers, cookie=cookie) cookie += '; '+ headers['Cookie'] headers = {'Referer': url, 'Cookie': cookie, 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.81 Safari/537.36'} r = client.request(url, headers=headers) r = client.parseDOM(r, 'div', attrs={'class': 'title'}) r = [zip(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a')) for i in r] r = [i[0] for i in r] r = [i[0] for i in r if (cleantitle.get(title) in cleantitle.get(i[1]))][0] url = {'imdb': imdb, 'title': title, 'year': year, 'url': r, 'headers': headers} url = urllib.urlencode(url) return url except: return
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) headers = eval(data['headers']) aliases = eval(data['aliases']) title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title'] title = cleantitle.getsearch(title) query = self.search_link % (urllib.quote_plus(title)) query = urlparse.urljoin(self.base_link, query) r = client.request(query, headers=headers, timeout='30', mobile=True) match = re.compile('alias=(.+?)\'">(.+?)</a>').findall(r) r = [(i[0], re.findall('(.+?)\s+-\s+Season\s+(\d+)', i[1])) for i in match] r = [(i[0], i[1][0][0], i[1][0][1]) for i in r if len(i[1]) > 0] r = [i[0] for i in r if self.matchAlias(i[1], aliases) and int(season) == int(i[2])][0] url = {'type': 'tvshow', 'id': r, 'episode': episode, 'season': season, 'headers': headers} url = urllib.urlencode(url) return url except: return
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: if (self.user == '' or self.password == ''): raise Exception() if url == None: return url = urlparse.urljoin(self.base_link, url) r = client.request(url, headers=self.headers) r = json.loads(r)['episodes'] r = [(str(i['id']), str(i['season']), str(i['number']), str(i['airdate'])) for i in r] url = [i for i in r if season == '%01d' % int(i[1]) and episode == '%01d' % int(i[2])] url += [i for i in r if premiered == i[3]] url= self.episode_link % url[0][0] return url except: return
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources if (self.user == '' or self.password == ''): raise Exception() url = urlparse.urljoin(self.base_link, url) url = client.request(url, headers=self.headers) url = json.loads(url)['url'] sources.append({'source': 'ororo', 'quality': 'HD', 'language': 'en', 'url': url, 'direct': True, 'debridonly': False}) return sources except: return sources
def movie(self, imdb, title, localtitle, aliases, year): try: query = self.search_link % (urllib.quote_plus(title)) query = urlparse.urljoin(self.base_link, query) t = cleantitle.get(title) y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0'] r = client.request(query) r = dom_parser.parse_dom(r, 'div', attrs={'class': 'item'}) r = [(dom_parser.parse_dom(i, 'a', attrs={'class': 'cluetip'}, req='href'), dom_parser.parse_dom(i, 'div', attrs={'class': 'description'})) for i in r] r = [(i[0][0].attrs['href'], dom_parser.parse_dom(i[1], 'h3', attrs={'class': 'text-nowrap'}), dom_parser.parse_dom(i[1], 'div', attrs={'class': 'meta'})) for i in r if i[0] and i[1]] r = [(i[0], i[1][0].content, dom_parser.parse_dom(i[2], 'span', attrs={'class': 'pull-left'})) for i in r if i[0] and i[1] and i[2]] r = [(i[0], i[1], re.sub('[^\d]+', '', i[2][0].content)) for i in r if i[2]] r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year r = [i[0] for i in r if cleantitle.get(i[1]) == t and i[2] in y][0] return source_utils.strip_domain(r) except: return
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) year = re.findall('(\d{4})', premiered)[0] if int(year) >= 2016: raise Exception() url = re.sub('[^A-Za-z0-9]', '-', data['tvshowtitle']).lower() url = self.tvsearch_link % (url, data['year'], '%01d' % int(season), '%01d' % int(episode)) r = urlparse.urljoin(self.base_link, url) r = client.request(r, output='geturl') if not data['year'] in r: raise Exception() return url except: return
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: if url == None: return tv_maze = tvmaze.tvMaze() num = tv_maze.episodeAbsoluteNumber(tvdb, int(season), int(episode)) num = str(num) url = urlparse.urljoin(self.base_link, url) r = client.request(url) r = client.parseDOM(r, 'tr', attrs = {'class': ''}) r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'td', attrs = {'class': 'epnum'})) for i in r] r = [(i[0][0], i[1][0]) for i in r if len(i[0]) > 0 and len(i[1]) > 0] r = [i[0] for i in r if num == i[1]][0] url = re.findall('(?://.+?|)(/.+)', r)[0] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: return
def sezonlukdizi_tvcache(self): try: url = urlparse.urljoin(self.base_link, self.search_link) result = client.request(url, redirect=False) if not result: r = client.request(self.base_link) r = dom_parser.parse_dom(r, 'script', attrs={'type': 'text/javascript', 'src': re.compile('.*/js/dizi.*')}, req='src')[0] url = urlparse.urljoin(self.base_link, r.attrs['src']) result = client.request(url) result = re.compile('{(.+?)}').findall(result) result = [(re.findall('u\s*:\s*(?:\'|\")(.+?)(?:\'|\")', i), re.findall('d\s*:\s*(?:\'|\")(.+?)(?:\',|\")', i)) for i in result] result = [(i[0][0], i[1][0]) for i in result if len(i[0]) > 0 and len(i[1]) > 0] result = [(re.compile('/diziler(/.+?)(?://|\.|$)').findall(i[0]), re.sub('&#\d*;', '', i[1])) for i in result] result = [(i[0][0] + '/', cleantitle.query(i[1])) for i in result if len(i[0]) > 0] return result except: return []
def movie(self, imdb, title, localtitle, aliases, year): try: query = self.search_link % (urllib.quote_plus(title)) query = urlparse.urljoin(self.base_link, query) c, h = self.__get_cookies(query) t = cleantitle.get(title) r = client.request(query, headers=h, cookie=c) r = client.parseDOM(r, 'div', attrs={'class': 'cell_container'}) r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a', ret='title')) for i in r] r = [(i[0][0], i[1][0]) for i in r if len(i[0]) > 0 and len(i[1]) > 0] r = [(i[0], re.findall('(.+?) \((\d{4})', i[1])) for i in r] r = [(i[0], i[1][0][0], i[1][0][1]) for i in r if len(i[1]) > 0] r = [i[0] for i in r if t == cleantitle.get(i[1]) and year == i[2]][0] url = re.findall('(?://.+?|)(/.+)', r)[0] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: return
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: if not url: return data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) url = self.__search([data['tvshowtitle']] + source_utils.aliases_to_array(eval(data['aliases'])), data['year'], season) if not url: return r = client.request(urlparse.urljoin(self.base_link, url)) r = dom_parser.parse_dom(r, 'div', attrs={'class': 'ep_link'}) r = dom_parser.parse_dom(r, 'a', req='href') r = [(i.attrs['href'], i.content) for i in r if i] r = [(i[0], re.findall("^(?:episode)\s*(\d+)$", i[1], re.I)) for i in r] r = [(i[0], i[1][0] if i[1] else '0') for i in r] r = [i[0] for i in r if int(i[1]) == int(episode)][0] return source_utils.strip_domain(r) except: return
def searchMovie(self, title, year, aliases, headers): try: title = cleantitle.normalize(title) url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(cleantitle.getsearch(title))) r = client.request(url, headers=headers, timeout='15') r = client.parseDOM(r, 'div', attrs={'class': 'ml-item'}) r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a', ret='title')) results = [(i[0], i[1], re.findall('\((\d{4})', i[1])) for i in r] try: r = [(i[0], i[1], i[2][0]) for i in results if len(i[2]) > 0] url = [i[0] for i in r if self.matchAlias(i[1], aliases) and (year == i[2])][0] except: url = None pass if (url == None): url = [i[0] for i in results if self.matchAlias(i[1], aliases)][0] url = '%s/watch/' % url return url except: return
def searchMovie(self, title, year, aliases, headers): try: title = cleantitle.normalize(title) url = urlparse.urljoin(self.base_link, self.search_link % (cleantitle.geturl(title.replace('\'', '-')))) r = client.request(url, timeout='10', headers=headers) r = client.parseDOM(r, 'h2', attrs={'class': 'tit'}) r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a', ret='title')) for i in r] r = [(i[0][0], i[1][0]) for i in r if len(i[0]) > 0 and len(i[1]) > 0] r = [(i[0], re.findall('(.+?) \((\d{4})', i[1])) for i in r] r = [(i[0], i[1][0][0], i[1][0][1]) for i in r if len(i[1]) > 0] try: match = [i[0] for i in r if self.matchAlias(i[1], aliases) and year == i[2]][0] except: match = [i[0] for i in r if self.matchAlias(i[1], aliases)][0] url = re.findall('(?://.+?|)(/.+)', match)[0] url = client.replaceHTMLCodes(url) return url.encode('utf-8') except: return
def __search(self, title, localtitle, year, content_type): try: t = cleantitle.get(title) tq = cleantitle.get(localtitle) y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0'] query = urlparse.urljoin(self.base_link, self.search_link) post = urllib.urlencode({'k': "%s"}) % tq r = client.request(query, post=post) r = json.loads(r) r = [i.get('result') for i in r if i.get('type', '').encode('utf-8') == content_type] r = [(i.get('url'), i.get('originalTitle'), i.get('title'), i.get('anneeProduction', 0), i.get('dateStart', 0)) for i in r] r = [(i[0], re.sub('<.+?>|</.+?>', '', i[1] if i[1] else ''), re.sub('<.+?>|</.+?>', '', i[2] if i[2] else ''), i[3] if i[3] else re.findall('(\d{4})', i[4])[0]) for i in r if i[3] or i[4]] r = sorted(r, key=lambda i: int(i[3]), reverse=True) # with year > no year r = [i[0] for i in r if i[3] in y and (t.lower() == cleantitle.get(i[1].lower()) or tq.lower() == cleantitle.query(i[2].lower()))][0] url = re.findall('(?://.+?|)(/.+)', r)[0] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: return
def __search(self, titles, year, season='0'): try: query = urlparse.urljoin(self.base_link, self.search_link) t = [cleantitle.get(i) for i in set(titles) if i] y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0'] r = client.request(query, post={'do': 'search', 'subaction': 'search', 'search_start': 0, 'full_search': 0, 'result_from': 1, 'story': cleantitle.query(titles[0])}) r = dom_parser.parse_dom(r, 'div', attrs={'class': 'fullstream'}) r = [(dom_parser.parse_dom(i, 'h3', attrs={'class': 'mov-title'}), dom_parser.parse_dom(i, 'div', attrs={'class': 'fullmask'})) for i in r] r = [(dom_parser.parse_dom(i[0], 'a', req='href'), dom_parser.parse_dom(i[1], 'a', attrs={'href': re.compile('.*/year/\d+')})) for i in r] r = [(i[0][0].attrs['href'], i[0][0].content, i[1][0].content if i[1] else '0') for i in r if i[0]] r = [(i[0], i[1], i[2], re.findall('(.+?)\s+(?:\s*-\s*saison)\s+(\d+)', i[1], re.I)) for i in r] r = [(i[0], i[3][0][0] if len(i[3]) > 0 else i[1], i[2], i[3][0][1] if len(i[3]) > 0 else '0') for i in r] r = [(i[0], i[1], i[2], '1' if int(season) > 0 and i[3] == '0' else i[3]) for i in r] r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y and int(i[3]) == int(season)][0] return source_utils.strip_domain(r) except: return
def __search(self, title, season): try: query = self.search_link % (urllib.quote_plus(cleantitle.query(title))) query = urlparse.urljoin(self.base_link, query) t = cleantitle.get(title) r = client.request(query) r = client.parseDOM(r, 'div', attrs={'class': 'moviefilm'}) r = client.parseDOM(r, 'div', attrs={'class': 'movief'}) r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a')) for i in r] r = [(i[0][0], i[1][0].lower()) for i in r if len(i[0]) > 0 and len(i[1]) > 0] r = [(i[0], i[1], re.findall('(.+?)\s+(?:saison)\s+(\d+)', i[1])) for i in r] r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1], i[2][0][1] if len(i[2]) > 0 else '0') for i in r] r = [(i[0], i[1], re.findall('\((.+?)\)$', i[1]), i[2]) for i in r] r = [(i[0], i[2][0] if len(i[2]) > 0 else i[1], i[3]) for i in r] r = [i[0] for i in r if t == cleantitle.get(i[1]) and int(i[2]) == int(season)][0] url = re.findall('(?://.+?|)(/.+)', r)[0] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: return
def __search(self, title, year): try: query = self.search_link % (urllib.quote_plus(cleantitle.query(title))) query = urlparse.urljoin(self.base_link, query) t = cleantitle.get(title) y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0'] r = client.request(query) r = dom_parser.parse_dom(r, 'div', attrs={'class': 'movie_single'}) r = dom_parser.parse_dom(r, 'a', attrs={'class': 'unfilm'}, req='href') r = [(i.attrs['href'], dom_parser.parse_dom(r, 'div', attrs={'class': 'title'}), dom_parser.parse_dom(r, 'span', attrs={'class': 'post-year'})) for i in r] r = [(i[0], re.sub('<.+?>|</.+?>', '', i[1][0].content), i[2][0].content if i[2] else '0') for i in r if i[1]] r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year r = [i[0] for i in r if t == cleantitle.get(i[1]) and i[2] in y][0] return source_utils.strip_domain(r) except: return
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: if url == None: return url = urlparse.urljoin(self.base_link, url) result = client.request(url) result = client.parseDOM(result, 'ul', attrs={'data-season-num': season})[0] result = client.parseDOM(result, 'li') for i in result: s = client.parseDOM(i, 'a', attrs={'class': 'episodeNum'})[0] e = int(s[7:-1]) if e == int(episode): return client.parseDOM(i, 'a', attrs={'class': 'episodeNum'}, ret='href')[0] except : return
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources url = urlparse.urljoin(self.base_link, url) result = client.request(url) result = client.parseDOM(result, 'div', attrs={'id': 'links'}) attr = client.parseDOM(result, 'ul', ret='data-type') result = client.parseDOM(result, 'ul') for x in range(0, len(result)): transl_type = attr[x] links = result[x] sources += self.extract_sources(transl_type, links) return sources except: return sources
def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year): try: query = self.search_link % (urllib.quote_plus(tvshowtitle)) query = urlparse.urljoin(self.base_link, query) result = client.request(query) result = client.parseDOM(result, 'div', attrs={'class': 'movie clearfix'}) result = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'span', attrs={'class': 'title-pl'}), client.parseDOM(i, 'span', attrs={'class': 'title-en'}), client.parseDOM(i, 'img', ret='src'), client.parseDOM(i, 'p'), client.parseDOM(i, 'p', attrs={'class': 'plot'})) for i in result ] result = [(i[0][0], u" ".join(i[1] + i[2]), re.findall('(\d{4})', i[4][0])) for i in result] result = [i for i in result if 'serial' in i[0]] result = [i for i in result if cleantitle.get(tvshowtitle) in cleantitle.get(i[1])] years = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1)] result = [i[0] for i in result if any(x in i[2] for x in years)][0] url = result return url except: return
def crazy_cookie_hash(self, mycookie): tmp = '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' tmp = base64.b64decode(tmp) _myFun = compile(tmp, '', 'exec') vGlobals = {"__builtins__": None, 'len': len, 'list': list, 'ord': ord, 'range': range} vLocals = {'abc': ''} exec _myFun in vGlobals, vLocals myFun1 = vLocals['abc'] data = client.request(urlparse.urljoin(self.base_link, '/jsverify.php?op=tag'), cookie=mycookie) data = byteify(json.loads(data)) d = {} for i in range(len(data['key'])): d[data['key'][i]] = data['hash'][i] tmp = '' for k in sorted(d.keys()): tmp += d[k] mycookie = 'tmvh=%s;%s' % (myFun1(tmp), mycookie) return mycookie
def do_search(self, title, year, video_type): try: url = urlparse.urljoin(self.base_link, self.search_link) url = url % urllib.quote_plus(cleantitle.query(title)) result = client.request(url) result = client.parseDOM(result, 'div', attrs={'class': 'item'}) for row in result: row_type = client.parseDOM(row, 'div', attrs={'class': 'typepost'})[0] if row_type != video_type: continue names = client.parseDOM(row, 'span', attrs={'class': 'tt'})[0] names = names.split('/') year_found = client.parseDOM(row, 'span', attrs={'class': 'year'}) if self.name_matches(names, title, year) and (len(year_found) == 0 or year_found[0] == year): url = client.parseDOM(row, 'a', ret='href')[0] return urlparse.urljoin(self.base_link, url) except : return
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: if not url: return data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) tvshowtitle = data['tvshowtitle'] localtvshowtitle = data['localtvshowtitle'] aliases = source_utils.aliases_to_array(eval(data['aliases'])) url = self.__search([localtvshowtitle] + aliases, data['year'], season) if not url and tvshowtitle != localtvshowtitle: url = self.__search([tvshowtitle] + aliases, data['year'], season) if not url: return r = client.request(urlparse.urljoin(self.base_link, url)) r = dom_parser.parse_dom(r, 'div', attrs={'id': 'list-episodes'}) r = dom_parser.parse_dom(r, 'h2') r = dom_parser.parse_dom(r, 'a', attrs={'href': re.compile('.*/episode-%s.*' % episode)}, req='href')[0].attrs['href'] return source_utils.strip_domain(r) except: return
def __search(self, titles, year, season='0'): try: query = self.search_link % (urllib.quote_plus(cleantitle.query(titles[0]))) query = urlparse.urljoin(self.base_link, query) t = [cleantitle.get(i) for i in set(titles) if i] y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0'] r = client.request(query) r = dom_parser.parse_dom(r, 'div', attrs={'id': 'featured'}) r = dom_parser.parse_dom(r, 'h2') r = dom_parser.parse_dom(r, 'a', req='href') r = [(i.attrs['href'], i.content.lower()) for i in r if i] r = [(i[0], i[1], re.findall('(.+?) \(*(\d{4})', i[1])) for i in r] r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1], i[2][0][1] if len(i[2]) > 0 else '0') for i in r] r = [(i[0], i[1], i[2], re.findall('(.+?)\s+(?:season|s)\s*(\d+)', i[1])) for i in r] r = [(i[0], i[3][0][0] if len(i[3]) > 0 else i[1], i[2], i[3][0][1] if len(i[3]) > 0 else '0') for i in r] r = [(i[0], i[1], i[2], '1' if int(season) > 0 and i[3] == '0' else i[3]) for i in r] r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y and int(i[3]) == int(season)][0] return source_utils.strip_domain(r) except: return
def __search(self, titles): try: query = self.search_link % urllib.quote_plus(cleantitle.query(titles[0])) query = urlparse.urljoin(self.base_link, query) t = [cleantitle.get(i) for i in set(titles) if i] r = client.request(query) r = dom_parser.parse_dom(r, 'article') r = dom_parser.parse_dom(r, 'h2', attrs={'class': 'entry-title'}) r = dom_parser.parse_dom(r, 'a', req='href') r = [(i.attrs['href'], i.content) for i in r] r = [(i[0]) for i in r if cleantitle.get(i[1]) in t][0] return source_utils.strip_domain(r) except: return
def __search(self, titles): try: query = self.search_link % urllib.quote_plus(cleantitle.query(titles[0])) query = urlparse.urljoin(self.base_link, query) t = [cleantitle.get(i) for i in set(titles) if i] r = client.request(query) r = dom_parser.parse_dom(r, 'div', attrs={'id': 'container-search'}) r = dom_parser.parse_dom(r, 'div', attrs={'class': 'movie-cat'}) r = dom_parser.parse_dom(r, 'h4', attrs={'class': 'title'}) r = dom_parser.parse_dom(r, 'a', req=['title', 'href']) r = [(i.attrs['href'], i.attrs['title']) for i in r] r = [(i[0]) for i in r if cleantitle.get(i[1]) in t][0] return source_utils.strip_domain(r) except: return
def __get_episode_link(self, url, episode='1'): try: if not url: return url = urlparse.urljoin(self.base_link, url) r = client.request(url) r = dom_parser.parse_dom(r, 'div', attrs={'id': 'list-espisode'}) r = dom_parser.parse_dom(r, 'div', attrs={'class': 'movie-item-espisode'}) r = dom_parser.parse_dom(r, 'a', req='href') r = [(i.attrs['href'], i.content) for i in r] r = [(i[0], re.findall('EP\s*(\d+)$', i[1])) for i in r] r = [i[0] for i in r if i[1] and int(i[1][0]) == int(episode)][0] return source_utils.strip_domain(r) except: return
def __search(self, titles, year): try: n = cache.get(self.__get_nonce, 24) query = self.search_link % (urllib.quote_plus(cleantitle.query(titles[0])), n) query = urlparse.urljoin(self.base_link, query) t = [cleantitle.get(i) for i in set(titles) if i] y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0'] r = client.request(query) r = json.loads(r) r = [(r[i].get('url'), r[i].get('title'), r[i].get('extra').get('date')) for i in r] r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y][0] return source_utils.strip_domain(r) except: return
def __search(self, titles): try: query = self.search_link % urllib.quote_plus(cleantitle.query(titles[0])) query = urlparse.urljoin(self.base_link, query) t = [cleantitle.get(i) for i in set(titles) if i] r = client.request(query, XHR=True) r = json.loads(r) r = [(i.get('url'), i.get('name'))for i in r] r = [(i[0]) for i in r if cleantitle.get(i[1]) in t][0] return source_utils.strip_domain(r) except: return
def __get_episode_link(self, url, episode='1'): try: if not url: return url = urlparse.urljoin(self.base_link, url) r = client.request(url) r = dom_parser.parse_dom(r, 'ul', attrs={'class': 'all-episode'}) r = dom_parser.parse_dom(r, 'li') r = dom_parser.parse_dom(r, 'a', attrs={'href': re.compile('.*-episode-%s\.\w+.*?' % episode)}, req='href')[0].attrs['href'] return source_utils.strip_domain(r) except: return
def __search(self, titles, year): try: query = self.search_link % (urllib.quote_plus(cleantitle.query(titles[0]))) query = urlparse.urljoin(self.base_link, query) t = [cleantitle.get(i) for i in set(titles) if i] y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0'] r = client.request(query, XHR=True, referer=self.base_link) r = dom_parser.parse_dom(r, 'a', req='href') r = [(i.attrs['href'], i.content.lower()) for i in r if i] r = [(i[0], i[1], re.findall('(.+?) \(*(\d{4})', i[1])) for i in r] r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1], i[2][0][1] if len(i[2]) > 0 else '0') for i in r] r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y][0] return source_utils.strip_domain(r) except: return
def __search(self, titles, year): try: query = self.search_link % (urllib.quote_plus(cleantitle.query(titles[0]))) query = urlparse.urljoin(self.base_link, query) t = [cleantitle.get(i) for i in set(titles) if i] y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0'] r = client.request(query) r = dom_parser.parse_dom(r, 'div', attrs={'id': 'list-drama'}) r = dom_parser.parse_dom(r, 'div', attrs={'class': 'media'}) r = [dom_parser.parse_dom(i, 'div', attrs={'class': 'media-body'}) for i in r] r = [(dom_parser.parse_dom(i[0], 'a', req='href'), dom_parser.parse_dom(i[0], 'small', attrs={'class': 'pull-right'})) for i in r if i] r = [(i[0][0].attrs['href'], i[0][0].content, re.sub('<.+?>|</.+?>', '', i[1][0].content)) for i in r if i[0] and i[1]] r = [(i[0], i[1], re.findall('(\d{4})', i[2])) for i in r] r = [(i[0], i[1], i[2][0] if i[2] else '0') for i in r] r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y][0] return source_utils.strip_domain(r) except: return
def __search(self, titles, year): try: t = [cleantitle.get(i) for i in set(titles) if i] y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0'] r = client.request(urlparse.urljoin(self.base_link, self.search_link), post={'query': titles[0]}) r = dom_parser.parse_dom(r, 'li', attrs={'class': 'entTd'}) r = dom_parser.parse_dom(r, 'div', attrs={'class': 've-screen'}, req='title') r = [(dom_parser.parse_dom(i, 'a', req='href'), i.attrs['title'].split(' - ')[0]) for i in r] r = [(i[0][0].attrs['href'], i[1], re.findall('(.+?) \(*(\d{4})', i[1])) for i in r] r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1], i[2][0][1] if len(i[2]) > 0 else '0') for i in r] r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y][0] return source_utils.strip_domain(r) except: return
def __search(self, titles, year): try: query = self.search_link % (urllib.quote_plus(titles[0])) query = urlparse.urljoin(self.base_link, query) t = [cleantitle.get(i) for i in set(titles) if i] y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0'] r = client.request(query, XHR=True) if r and r.startswith('{'): r = '[%s]' % r r = json.loads(r) r = [(i['url'], i['name']) for i in r if 'name' in i and 'url' in i] r = [(i[0], i[1], re.findall('(.+?) \(*(\d{4})?\)*$', i[1])) for i in r] r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1], i[2][0][1] if len(i[2]) > 0 else '0') for i in r] r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y][0] url = source_utils.strip_domain(r) url = url.replace('serien/', '') return url except: return
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: if not url: return url = urlparse.urljoin(self.base_link, url) url = client.request(url, output='geturl') if season == 1 and episode == 1: season = episode = '' r = client.request(url) r = dom_parser.parse_dom(r, 'ul', attrs={'class': 'episodios'}) r = dom_parser.parse_dom(r, 'a', attrs={'href': re.compile('[^\'"]*%s' % ('-%sx%s' % (season, episode)))})[0].attrs['href'] return source_utils.strip_domain(r) except: return
def resolve(self, url): try: url = urlparse.urljoin(self.base_link, url) r = client.request(url, referer=self.base_link) r = json.loads(r)['Stream'] r = [(dom_parser.parse_dom(r, 'a', req='href'), dom_parser.parse_dom(r, 'iframe', req='src'))] r = [i[0][0].attrs['href'] if i[0] else i[1][0].attrs['src'] for i in r if i[0] or i[1]][0] if not r.startswith('http'): r = urlparse.parse_qs(r) r = [r[i][0] if r[i] and r[i][0].startswith('http') else (i, '') for i in r][0] return r except: return
def __search(self, imdb): try: l = ['1', '15'] r = client.request(urlparse.urljoin(self.base_link, self.search_link % imdb)) r = dom_parser.parse_dom(r, 'table', attrs={'id': 'RsltTableStatic'}) r = dom_parser.parse_dom(r, 'tr') r = [(dom_parser.parse_dom(i, 'a', req='href'), dom_parser.parse_dom(i, 'img', attrs={'alt': 'language'}, req='src')) for i in r] r = [(i[0][0].attrs['href'], i[0][0].content, i[1][0].attrs['src']) for i in r if i[0] and i[1]] r = [(i[0], i[1], re.findall('.+?(\d+)\.', i[2])) for i in r] r = [(i[0], i[1], i[2][0] if len(i[2]) > 0 else '0') for i in r] r = sorted(r, key=lambda i: int(i[2])) # german > german/subbed r = [i[0] for i in r if i[2] in l][0] return source_utils.strip_domain(r) except: return