Best Python code snippet using gabbi_python
__init__.py
Source:__init__.py
...647 data = self._url_re.sub(functools.partial(self._url_replace, path), data)648 return "{% raw %}<style type=\"text/css\">\n" + data + "\n</style>{% endraw %}"649 tagcontent = match.group("attributes")650 return '<link%s%s>' % (tagcontent, "" if tagcontent[-1] == "/" else "/")651 def _url_replace(self, path, match):652 url = match.group("url").strip("'").strip("\"")653 if self._check_uri(url):654 path = os.path.dirname(path)655 if url.startswith("/") or not path:656 absurl = self.static + "/" + url.lstrip("/")657 else:658 absurl = path + "/" + url659 absurl = os.path.normpath(absurl).replace(os.sep, "/")660 if absurl.startswith(self.static + "/"):661 url = absurl[len(self.static)+1:]662 ext = url[url.rfind(".")+1:]663 if ext in ("gif", "png", "jpg") and utils.get_resource_exists(absurl):664 data = "data:image/" + ext + ";base64," + base64.b64encode(utils.get_resource_data(absurl))665 return "url({% endraw %}{% if uridata_support %}" + data + "{% else %}'" + url + "'{% endif %}{% raw %})"...
1.text_cleaning.py
Source:1.text_cleaning.py
...64 text = text.strip()65 for rgx in remove_regx_map:66 text = re.sub(rgx, remove_regx_map[rgx], text)67 return text68def _url_replace(text):69 """ url é¾æ¥æ¿æ¢ï¼æ³¨æçæ¡ä¸ä¹åå¨ urlï¼é¢æµå®çæ¡åå mapping åæ¥ """70 for url in url_map_dict:71 if url in text:72 text = text.replace(url, url_map_dict[url])73 return text74def _clean_duplacte_words(text):75 """76 å»é¤å¾å¤éå¤çè¯åæ ç¹ç¬¦å·77 """78 reg = r'([^0-9IX]+)(\1){2,}'79 for i in range(6):80 temp = text81 text = re.sub(reg, lambda m: m.group(1), text)82 if len(text) == len(temp):83 break84 return text85def clean_document(document, answers=None):86 title = document['title']87 paragraphs = document['paragraphs']88 # --------------------- clean title ---------------------89 title = _remove_html_tag(title)90 title = _remove_by_regex(title)91 # remove website name92 if '_' in title:93 title = ''.join(title.split('_')[:-1])94 elif '-' in title:95 title = ''.join(title.split('-')[:-1])96 # --------------------- clean paragraphs ---------------------97 # ans_has_html = re.match('<[a-zA-Z]+>', ''.join(answers), flags=0) is not None98 new_paragraphs = []99 for paragraph in paragraphs:100 # 大éurlé¾æ¥çæ¸
æ´101 paragraph = paragraph.replace('httpï¼//', 'http://')102 paragraph = paragraph.replace('httpsï¼//', 'https://')103 paragraph = _url_replace(paragraph)104 # å¦æçæ¡å
å«æ ç¾åä¸æ¸
æ´htmlæ ç¾105 # if not ans_has_html:106 paragraph = _remove_html_tag(paragraph)107 # é误è¯ççº æ£108 paragraph = _clean_error_word(paragraph)109 # æç
§æ£å表达å¼å»é¤ç¹å®ææ¬110 paragraph = _remove_by_regex(paragraph)111 # å»é¤ç©ºæ ¼112 paragraph = _remove_space(paragraph)113 # å»é¤éå¤çè¯114 paragraph = _clean_duplacte_words(paragraph)115 # å»é¤ç©ºæ®µè½åéå¤æ®µè½116 if paragraph != '' and paragraph not in new_paragraphs:117 new_paragraphs.append(paragraph)...
test.py
Source:test.py
...18 c = re.compile(p)19 print c.match('Isaac Asimov')20 21def test2():22 def _url_replace(matchobj):23 return '<a href=\'http://www.15yueliang.com\'>%s</a>'%matchobj.group('mp')24 a='''<a go='http://wwwbaidu.com'>123</a>456<a go='http://www.youxi.com'>112233</a>'''25 rs=re.subn('<a go=\'.*?\'>(?P<mp>.*?)</a>',_url_replace,a)26 print rs27def test3():28 s='<div class="goods_ref" itemprop="6910"><a isconvert="1" href="http://detail.tmall.com/item.htm?id=43538143059" rel="nofollow" target="_blank"><img src="http://img2.tbcdn.cn/tfscom/i3/749311050/TB2Zt9XhFXXXXXhXpXXXXXXXXXX_!!749311050.jpg"/></a><a isconvert="1" href="http://detail.tmall.com/item.htm?id=43538143059" rel="nofollow" target="_blank"><h3>è´äº² å¤åè½æä¹³æ å奶æåå¦åºä¹³æåºä¹³æå«å奶æ¤è
° å©´å¿æ±æ</h3></a><div class="info"><em>ä»·æ ¼:</em><span class="price">249.00å
å
é®</span><span class="mall"><a href="http://www.15yueliang.com/go/tmall/mall/0.html" rel="nofollow" target="_blank">天ç«</a></span><span class="volume">éé:27</span></div><div class="ad"></div></div>'29 30 m=re.match(r'<div class=["\']{1}goods_ref["\']{1}.*?</div></div>',s)31 print m32if __name__ == '__main__': 33 # print test2()%({'meida_url':'http://www.youxi16.com'})34 # test2()...
Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.
You could also refer to video tutorials over LambdaTest YouTube channel to get step by step demonstration from industry experts.
Get 100 minutes of automation test minutes FREE!!