KAMI911 /
osm_poi_matchmaker
| Conditions | 41 |
| Total Lines | 139 |
| Code Lines | 106 |
| Lines | 0 |
| Ratio | 0 % |
| Changes | 0 | ||
Small methods make your code easier to understand, in particular if combined with a good name. Besides, if your method is small, finding a good name is usually much easier.
For example, if you find yourself adding comments to a method's body, this is usually a good sign to extract the commented part to a new method, and use the comment as a starting point when coming up with a good name for this new method.
Commonly applied refactorings include:
If many parameters/temporary variables are present:
Complex classes like osm_poi_matchmaker.dataproviders.hu_posta.hu_posta.process() often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
| 1 | # -*- coding: utf-8 -*- |
||
| 71 | def process(self): |
||
| 72 | try: |
||
| 73 | soup = save_downloaded_soup('{}'.format(self.link), os.path.join(self.download_cache, self.filename), |
||
| 74 | self.filetype) |
||
| 75 | for e in soup.findAll('post'): |
||
| 76 | try: |
||
| 77 | # If this is a closed post office, skip it |
||
| 78 | # if e.get('ispostpoint') == '0': |
||
| 79 | # continue |
||
| 80 | # The 'kirendeltség' post offices are not available to end users, so we remove them |
||
| 81 | if 'okmányiroda' in e.find('name').get_text().lower() or \ |
||
| 82 | 'mol kirendeltség' in e.find('name').get_text().lower(): |
||
| 83 | logging.debug('Skipping non public post office.') |
||
| 84 | continue |
||
| 85 | else: |
||
| 86 | if e.servicepointtype.get_text() == 'PM': |
||
| 87 | self.data.name = 'Posta' |
||
| 88 | self.data.code = 'hupostapo' |
||
| 89 | self.data.public_holiday_open = False |
||
| 90 | elif e.servicepointtype.get_text() == 'CS': |
||
| 91 | self.data.name = 'Posta csomagautomata' |
||
| 92 | self.data.code = 'hupostacso' |
||
| 93 | self.data.public_holiday_open = True |
||
| 94 | elif e.servicepointtype.get_text() == 'PP': |
||
| 95 | self.data.name = 'PostaPont' |
||
| 96 | self.data.code = 'hupostapp' |
||
| 97 | self.data.public_holiday_open = False |
||
| 98 | else: |
||
| 99 | logging.error('Non existing Posta type.') |
||
| 100 | self.data.postcode = e.get('zipcode') |
||
| 101 | self.data.housenumber = e.street.housenumber.get_text().split('(', 1)[0].strip() \ |
||
| 102 | if e.street.housenumber is not None else None |
||
| 103 | self.data.conscriptionnumber = None |
||
| 104 | self.data.city = clean_city(e.city.get_text()) |
||
| 105 | self.data.branch = e.find('name').get_text( |
||
| 106 | ) if e.find('name') is not None else None |
||
| 107 | if self.data.code == 'hupostapo': |
||
| 108 | self.data.branch = re.sub( |
||
| 109 | r"(\d{1,3})", r"\1. számú", self.data.branch) |
||
| 110 | days = e.findAll('days') if e.findAll( |
||
| 111 | 'days') is not None else None |
||
| 112 | nonstop_num = 0 |
||
| 113 | for d in days: |
||
| 114 | if len(d) != 0: |
||
| 115 | day_key = None |
||
| 116 | # Try to match day name in data source (day tag) with on of WeekDaysLongHU enum element |
||
| 117 | # Select day based on d.day matching |
||
| 118 | for rd in WeekDaysLongHU: |
||
| 119 | if rd.name == d.day.get_text(): |
||
| 120 | day_key = rd.value |
||
| 121 | break |
||
| 122 | else: |
||
| 123 | day_key = None |
||
| 124 | # No day matching skip to next |
||
| 125 | # Skip days that are not exist at data provider's |
||
| 126 | if day_key is None: |
||
| 127 | logging.warning('Cannot find any opening hours information for day {}.'. |
||
| 128 | format(rd.name)) |
||
| 129 | continue |
||
| 130 | else: |
||
| 131 | # Extract from and to information |
||
| 132 | from1 = d.from1.get_text() if d.from1 is not None else None |
||
| 133 | to1 = d.to1.get_text() if d.to1 is not None else None |
||
| 134 | from2 = d.from2.get_text() if d.from2 is not None else None |
||
| 135 | to2 = d.to2.get_text() if d.to2 is not None else None |
||
| 136 | # Avoid duplicated values of opening and close |
||
| 137 | if from1 != from2 and to1 != to2: |
||
| 138 | logging.debug('Opening hours in post office: %s: %s-%s; %s-%s.', |
||
| 139 | self.data.branch, from1, to1, from2, to2) |
||
| 140 | self.data.day_open(day_key, from1) |
||
| 141 | if from2 is None or to2 is None: |
||
| 142 | self.data.day_close(day_key, from1) |
||
| 143 | # Count opening hours with nonstop like settings |
||
| 144 | if from1 in '0:00' and to1 in ['0:00', '23:59', '24:00']: |
||
| 145 | nonstop_num += 1 |
||
| 146 | else: |
||
| 147 | # Check on Wednesday if there is a lunch break |
||
| 148 | # Only same lunch break is supported for every days |
||
| 149 | if day_key == 3: |
||
| 150 | self.data.lunch_break_start = to1 |
||
| 151 | self.data.lunch_break_stop = from2 |
||
| 152 | self.data.day_close(day_key, to2) |
||
| 153 | # Count opening hours with nonstop like settings |
||
| 154 | if from1 in '0:00' and to2 in ['0:00', '23:59', '24:00']: |
||
| 155 | nonstop_num += 1 |
||
| 156 | else: |
||
| 157 | # It seems there are duplications in Posta data source |
||
| 158 | # Remove duplicates |
||
| 159 | logging.warning('Dulicated opening hours in post office: %s: %s-%s; %s-%s.', |
||
| 160 | self.data.branch, from1, to1, from2, to2) |
||
| 161 | from2, to2 = None, None |
||
| 162 | # All times are open so it is non stop |
||
| 163 | if nonstop_num >= 7: |
||
| 164 | logging.debug('It is a non stop post office.') |
||
| 165 | self.data.nonstop = True |
||
| 166 | self.data.lat, self.data.lon = \ |
||
| 167 | check_hu_boundary(e.gpsdata.wgslat.get_text().replace(',', '.'), |
||
| 168 | e.gpsdata.wgslon.get_text().replace(',', '.')) |
||
| 169 | # Get street name and type |
||
| 170 | street_tmp_1 = clean_street(e.street.find('name').get_text().strip()) \ |
||
| 171 | if e.street.find('name') is not None else None |
||
| 172 | street_tmp_2 = clean_street_type(e.street.type.get_text().strip()) \ |
||
| 173 | if e.street.type is not None else None |
||
| 174 | # Streets without types |
||
| 175 | if street_tmp_2 is None: |
||
| 176 | self.data.street = street_tmp_1 |
||
| 177 | # Since there is no original address format we create one |
||
| 178 | if self.data.housenumber is not None: |
||
| 179 | self.data.original = '{} {}'.format( |
||
| 180 | street_tmp_1, self.data.housenumber) |
||
| 181 | else: |
||
| 182 | self.data.original = '{}'.format(street_tmp_1) |
||
| 183 | # Street with types |
||
| 184 | elif street_tmp_1 is not None and street_tmp_2 is not None: |
||
| 185 | self.data.street = '{} {}'.format( |
||
| 186 | street_tmp_1, street_tmp_2) |
||
| 187 | # Since there is no original address format we create one |
||
| 188 | if self.data.housenumber is not None: |
||
| 189 | self.data.original = '{} {} {}'.format(street_tmp_1, street_tmp_2, |
||
| 190 | self.data.housenumber) |
||
| 191 | else: |
||
| 192 | self.data.original = '{} {}'.format( |
||
| 193 | street_tmp_1, street_tmp_2) |
||
| 194 | else: |
||
| 195 | logging.error( |
||
| 196 | 'Non handled state in street data processing!') |
||
| 197 | self.data.phone = clean_phone_to_str(e.phonearea.get_text()) \ |
||
| 198 | if e.phonearea is not None else None |
||
| 199 | self.data.email = e.email.get_text().strip() if e.email is not None else None |
||
| 200 | self.data.add() |
||
| 201 | except Exception as err: |
||
| 202 | logging.error(err) |
||
| 203 | logging.error(e) |
||
| 204 | logging.exception('Exception occurred') |
||
| 205 | |||
| 206 | except Exception as err: |
||
| 207 | logging.exception('Exception occurred') |
||
| 208 | |||
| 209 | logging.error(err) |
||
| 210 |
Loading history...