May-13-2018, 08:56 PM
When I run this I get an "unexpected indent error" at 'def __init__ (self, infile):. When I remove the space that's marked, I get a "invalid syntax error".
I 'refurbished' this from what Lars60+ invented for me so this is just getting started.
As always - any help is most appreciated!
Thank you!
I 'refurbished' this from what Lars60+ invented for me so this is just getting started.
As always - any help is most appreciated!
Thank you!
import requests
from bs4 import BeautifulSoup
from pathlib import path
class GetCompletions:
def __init__(self, infile):
self.homepath = Path('.')
self.log.pdfpath = self.homepath / 'comppdf'
self.log.pdfpath.mkdir(exist_ok=True)
self.log.pdfpath = self.homepath / 'geocorepdf'
self.log.pdfpath.mkdir(exist_ok=True)
self.textpath = self.homepath / 'text'
self.text.mkdir(exist_ok=True)
self.infile = self.textpath / infile
self.api = []
self.parse_and_save(getpdfs=True)
"""Above will create a folder called comppdf, and wsgeo wherever the WOGCC
File Downloads file is run from as well as a text file for my api file to
reside."""
def get_url(self):
for entry in self.apis:
yield (entry, "http://wogcc.state.wy.us/wyocomp.cfm?nAPI=[]".format(entry[3:10]))
yield (entry, "http://wogcc.state.wy.us/whatupcores.cfm?autonum=[]".format(entry[3:10]))
"""Above will get the URL that matches my API numbers."""
def parse_and_save(self, getpdfs=False):
for file in filelist:
with file.open('r') as f:
soup = BeautifulSoup(f.read(), 'lxml')
if getpdfs:
links = soup.find_all('a')
for link in links:
url in link['href']
if 'www' in url:
continue
print('downloading pdf at: {}'.format(url))
p = url.index('=')
response = requests.get(url, stream=True, allow_redirects=False)
if response.status_code == 200:
try:
header_info = response.headers['Content-Disposition']
idx = header_info.index('filename')
filename = self.log_pdfpath / header[idx+9:]
except ValueError:
filename = self.log_path / 'comp{}'.format(url[p 1:])
print("couldn't locate filename for {} will use: {}".format(file, filename))
except KeyError
filename = self.log_pdfpath / 'comp{}.pdf'.format(url[p + 1:])
print('got KeyError on {}, respnse.headers = {}'.format(file, response.headers))
print('will use name: {}'.format(filename))
print(repsonse.headers)
with filename.open('wb') as f:
f.write(respnse.content)
sfname = self.textpath / 'summary_{}.txt'.format((file.name.split('_'))[1].split('.')[0][3:10])
tds = soup.find_all('td')
with sfname.open('w') as f:
for td in tds:
if td.txt
if any(field in td.text for field in self.fields):
f.write('{}\n'.format(td.text)
if__name__ == '__main__':
GetCompletions('api.txt')
