def run(self):
selectorClass = getattr(
eval(self.config['selector_type']),
self.config['selector_type'].title() + 'Selector')
results = dict()
results['project'] = self.args['<projectname>']
results['data'] = list()
try:
result = dict()
print()
print(Back.YELLOW + Fore.BLUE + "Loading page ", self.config['scraping']['url'] \
+ Back.RESET + Fore.RESET)
selector = selectorClass(self.config['scraping']['url'])
for attribute in self.config['scraping']['data']:
if attribute['field'] != "":
print("\nExtracting",
attribute['field'],
"attribute",
sep=' ')
result[attribute['field']] = selector.extract_content(
attribute['selector'], attribute['attr'],
attribute['default'])
if not self.config['scraping'].get('next'):
results['data'].append(result)
else:
for next in self.config['scraping']['next']:
for r in traverse_next(selector, next, result):
results['data'].append(r)
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
finally:
if self.args['--output_type'] == 'json':
import json
with open(os.path.join(os.getcwd(), self.args['<output_filename>'] + '.json'), \
'w') as f:
json.dump(results, f)
elif self.args['--output_type'] == 'csv':
import csv
with open(os.path.join(os.getcwd(), self.args['<output_filename>'] + '.csv'), \
'w') as f:
fields = extract_fieldnames(self.config)
writer = csv.DictWriter(f, fieldnames=fields)
writer.writeheader()
writer.writerows(results['data'])
print()
print(Back.WHITE + Fore.RED + self.args['<output_filename>'], \
".", self.args['--output_type'], " has been created" \
+ Back.RESET + Fore.RESET, sep="")
def run(self):
selectorClass = getattr(
eval(self.config['selector_type']),
self.config['selector_type'].title() + 'Selector'
)
results = dict()
results['project'] = self.args['<projectname>']
results['data'] = list()
try:
result = dict()
print()
print(Back.YELLOW + Fore.BLUE + "Loading page ", self.config['scraping']['url'] \
+ Back.RESET + Fore.RESET)
selector = selectorClass(self.config['scraping']['url'])
for attribute in self.config['scraping']['data']:
if attribute['field'] != "":
print("\nExtracting", attribute['field'], "attribute", sep=' ')
result[attribute['field']] = selector.extract_content(attribute['selector'], attribute['attr'], attribute['default'])
if not self.config['scraping'].get('next'):
results['data'].append(result)
else:
for next in self.config['scraping']['next']:
for r in traverse_next(selector, next, result):
results['data'].append(r)
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
finally:
if self.args['--output_type'] == 'json':
import json
with open(os.path.join(os.getcwd(), self.args['<output_filename>'] + '.json'), \
'w') as f:
json.dump(results, f)
elif self.args['--output_type'] == 'csv':
import csv
with open(os.path.join(os.getcwd(), self.args['<output_filename>'] + '.csv'), \
'w') as f:
fields = extract_fieldnames(self.config)
writer = csv.DictWriter(f, fieldnames=fields)
writer.writeheader()
writer.writerows(results['data'])
print()
print(Back.WHITE + Fore.RED + self.args['<output_filename>'], \
".", self.args['--output_type'], " has been created" \
+ Back.RESET + Fore.RESET, sep="")
def execute_command(self):
"""
The generate command uses `Jinja2 <http://jinja.pocoo.org/>`_ templates \
to create Python scripts, according to the specification in the configuration \
file. The predefined templates use the extract_content() method of the \
:ref:`selector classes <implementation-selectors>` to implement linear extractors \
and use recursive for loops to implement multiple levels of link crawlers. This \
implementation is effectively a representation of the traverse_next() \
:ref:`utility function <implementation-utils>`, using the loop depth to \
differentiate between levels of the crawler execution.
According to the --output_type argument in the CLI input, the results are \
written into a JSON document or a CSV document.
The Python script is written into <output_filename>.py - running this file \
is the equivalent of using the Scrapple :ref:`run command <command-run>`.
"""
print(Back.GREEN + Fore.BLACK + "Scrapple Generate")
print(Back.RESET + Fore.RESET)
directory = os.path.join(scrapple.__path__[0], 'templates', 'scripts')
with open(os.path.join(directory, 'generate.txt'), 'r') as f:
template_content = f.read()
template = Template(template_content)
try:
with open(self.args['<projectname>'] + '.json', 'r') as f:
config = json.load(f)
if self.args['--output_type'] == 'csv':
from scrapple.utils.config import extract_fieldnames
config['fields'] = str(extract_fieldnames(config))
config['output_file'] = self.args['<output_filename>']
config['output_type'] = self.args['--output_type']
rendered = template.render(config=config)
with open(self.args['<output_filename>'] + '.py', 'w') as f:
f.write(rendered)
print(Back.WHITE + Fore.RED + self.args['<output_filename>'], \
".py has been created" + Back.RESET + Fore.RESET, sep="")
except IOError:
print(Back.WHITE + Fore.RED + self.args['<projectname>'], ".json does not ", \
"exist. Use ``scrapple genconfig``." + Back.RESET + Fore.RESET, sep="")
def execute_command(self):
"""
The generate command uses `Jinja2 <http://jinja.pocoo.org/>`_ templates \
to create Python scripts, according to the specification in the configuration \
file. The predefined templates use the extract_content() method of the \
:ref:`selector classes <implementation-selectors>` to implement linear extractors \
and use recursive for loops to implement multiple levels of link crawlers. This \
implementation is effectively a representation of the traverse_next() \
:ref:`utility function <implementation-utils>`, using the loop depth to \
differentiate between levels of the crawler execution.
According to the --output_type argument in the CLI input, the results are \
written into a JSON document or a CSV document.
The Python script is written into <output_filename>.py - running this file \
is the equivalent of using the Scrapple :ref:`run command <command-run>`.
"""
print(Back.GREEN + Fore.BLACK + "Scrapple Generate")
print(Back.RESET + Fore.RESET)
directory = os.path.join(scrapple.__path__[0], 'templates', 'scripts')
with open(os.path.join(directory, 'generate.txt'), 'r') as f:
template_content = f.read()
template = Template(template_content)
try:
with open(self.args['<projectname>'] + '.json', 'r') as f:
config = json.load(f)
if self.args['--output_type'] == 'csv':
from scrapple.utils.config import extract_fieldnames
config['fields'] = str(extract_fieldnames(config))
config['output_file'] = self.args['<output_filename>']
config['output_type'] = self.args['--output_type']
rendered = template.render(config=config)
with open(self.args['<output_filename>'] + '.py', 'w') as f:
f.write(rendered)
print(Back.WHITE + Fore.RED + self.args['<output_filename>'], \
".py has been created" + Back.RESET + Fore.RESET, sep="")
except IOError:
print(Back.WHITE + Fore.RED + self.args['<projectname>'], ".json does not ", \
"exist. Use ``scrapple genconfig``." + Back.RESET + Fore.RESET, sep="")
def run(self):
selectorClass = getattr(
eval(self.config['selector_type']),
self.config['selector_type'].title() + 'Selector')
results = dict()
results['project'] = self.args['<projectname>']
results['data'] = list()
try:
result = dict()
tabular_data_headers = dict()
if self.args['--verbosity'] > 0:
print()
print(Back.YELLOW + Fore.BLUE + "Loading page ", self.config['scraping']['url'] \
+ Back.RESET + Fore.RESET, end='')
selector = selectorClass(self.config['scraping']['url'])
for attribute in self.config['scraping']['data']:
if attribute['field'] != "":
if self.args['--verbosity'] > 1:
print("\nExtracting",
attribute['field'],
"attribute",
sep=' ',
end='')
result[attribute['field']] = selector.extract_content(
**attribute)
if not self.config['scraping'].get('table'):
result_list = [result]
else:
tables = self.config['scraping'].get('table', [])
for table in tables:
if table.get('selector', '').strip() != '':
table.update({
'result': result,
'verbosity': self.args['--verbosity']
})
table_headers, result_list = selector.extract_tabular(
**table)
for th in table_headers:
if not th in tabular_data_headers:
tabular_data_headers[th] = len(
tabular_data_headers)
if not self.config['scraping'].get('next'):
results['data'].extend(result_list)
else:
for nextx in self.config['scraping']['next']:
for tdh, r in traverse_next(
selector,
nextx,
result,
verbosity=self.args['--verbosity']):
results['data'].append(r)
for th in tdh:
if not th in tabular_data_headers:
tabular_data_headers[th] = len(
tabular_data_headers)
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
finally:
if self.args['--output_type'] == 'json':
import json
with open(os.path.join(os.getcwd(), self.args['<output_filename>'] + '.json'), \
'w') as f:
json.dump(results, f, indent=3)
elif self.args['--output_type'] == 'csv':
import csv
with open(os.path.join(os.getcwd(), self.args['<output_filename>'] + '.csv'), \
'w') as f:
fields = extract_fieldnames(self.config)
data_headers = sorted(
tabular_data_headers,
key=lambda x: tabular_data_headers[x])
fields.extend(data_headers)
writer = csv.DictWriter(f, fieldnames=fields)
writer.writeheader()
writer.writerows(results['data'])
if self.args['--verbosity'] > 0:
print()
print(Back.WHITE + Fore.RED + self.args['<output_filename>'], \
".", self.args['--output_type'], " has been created" \
+ Back.RESET + Fore.RESET, sep="")
def run(self):
selectorClassMapping = {
'xpath': XpathSelector,
'css': CssSelector
}
selectorClass = selectorClassMapping.get(self.config['selector_type'].lower())
results = dict()
results['project'] = self.args['<projectname>']
results['data'] = list()
try:
result = dict()
tabular_data_headers = dict()
if self.args['--verbosity'] > 0:
print()
print(Back.YELLOW + Fore.BLUE + "Loading page ", self.config['scraping']['url'] \
+ Back.RESET + Fore.RESET, end='')
selector = selectorClass(self.config['scraping']['url'])
for attribute in self.config['scraping']['data']:
if attribute['field'] != "":
if self.args['--verbosity'] > 1:
print("\nExtracting", attribute['field'], "attribute", sep=' ', end='')
result[attribute['field']] = selector.extract_content(**attribute)
if not self.config['scraping'].get('table'):
result_list = [result]
else:
tables = self.config['scraping'].get('table', [])
for table in tables:
if table.get('selector', '').strip() != '':
table.update({
'result': result,
'verbosity': self.args['--verbosity']
})
table_headers, result_list = selector.extract_tabular(**table)
for th in table_headers:
if not th in tabular_data_headers:
tabular_data_headers[th] = len(tabular_data_headers)
if not self.config['scraping'].get('next'):
results['data'].extend(result_list)
else:
for nextx in self.config['scraping']['next']:
for tdh, r in traverse_next(selector, nextx, result, verbosity=self.args['--verbosity']):
results['data'].append(r)
for th in tdh:
if not th in tabular_data_headers:
tabular_data_headers[th] = len(tabular_data_headers)
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
finally:
if self.args['--output_type'] == 'json':
import json
with open(os.path.join(os.getcwd(), self.args['<output_filename>'] + '.json'), \
'w') as f:
json.dump(results, f, indent=4)
elif self.args['--output_type'] == 'csv':
import csv
with open(os.path.join(os.getcwd(), self.args['<output_filename>'] + '.csv'), \
'w') as f:
fields = extract_fieldnames(self.config)
data_headers = sorted(tabular_data_headers, key=lambda x:tabular_data_headers[x])
fields.extend(data_headers)
writer = csv.DictWriter(f, fieldnames=fields)
writer.writeheader()
writer.writerows(results['data'])
if self.args['--verbosity'] > 0:
print()
print(Back.WHITE + Fore.RED + self.args['<output_filename>'], \
".", self.args['--output_type'], " has been created" \
+ Back.RESET + Fore.RESET, sep="")
def run(self):
selectorClass = getattr(
eval(self.config['selector_type']),
self.config['selector_type'].title() + 'Selector'
)
results = dict()
results['project'] = self.args['<projectname>']
results['data'] = list()
try:
result = dict()
tabular_data_headers = dict()
print()
print(Back.YELLOW + Fore.BLUE + "Loading page ", self.config['scraping']['url'] \
+ Back.RESET + Fore.RESET)
selector = selectorClass(self.config['scraping']['url'])
for attribute in self.config['scraping']['data']:
if attribute['field'] != "":
print("\nExtracting", attribute['field'], "attribute", sep=' ')
result[attribute['field']] = selector.extract_content(attribute['selector'], attribute['attr'], attribute['default'])
if not self.config['scraping'].get('table'):
result_list = [result]
else:
tables = self.config['scraping'].get('table')
for table in tables:
table_headers, result_list = selector.extract_tabular(
result=result,
table_type=table.get('table_type', 'rows'),
header=table.get('header', []),
prefix=table.get('prefix', ''),
suffix=table.get('suffix', ''),
selector=table.get('selector', ''),
attr=table.get('attr', 'text'),
default=table.get('default', '')
)
for th in table_headers:
if not th in tabular_data_headers:
tabular_data_headers[th] = len(tabular_data_headers)
if not self.config['scraping'].get('next'):
results['data'].extend(result_list)
else:
for next in self.config['scraping']['next']:
for tdh, r in traverse_next(selector, next, result):
results['data'].append(r)
for th in tdh:
if not th in tabular_data_headers:
tabular_data_headers[th] = len(tabular_data_headers)
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
finally:
if self.args['--output_type'] == 'json':
import json
with open(os.path.join(os.getcwd(), self.args['<output_filename>'] + '.json'), \
'w') as f:
json.dump(results, f)
elif self.args['--output_type'] == 'csv':
import csv
with open(os.path.join(os.getcwd(), self.args['<output_filename>'] + '.csv'), \
'w') as f:
fields = extract_fieldnames(self.config)
data_headers = sorted(tabular_data_headers, key=lambda x:tabular_data_headers[x])
fields.extend(data_headers)
writer = csv.DictWriter(f, fieldnames=fields)
writer.writeheader()
writer.writerows(results['data'])
print()
print(Back.WHITE + Fore.RED + self.args['<output_filename>'], \
".", self.args['--output_type'], " has been created" \
+ Back.RESET + Fore.RESET, sep="")
