Unexpected indent / invalid syntax

[tjnichols]

All right! Lars60+ - I've made your change - awesome!

wavic - I've made your change - awesome!

Now I've got a traceback error.

Error:
 RESTART: C:\Users\toliver\AppData\Local\Programs\Python\Python36\WOGCC_File_Downloads.py 
Traceback (most recent call last):
  File "C:\Users\toliver\AppData\Local\Programs\Python\Python36\WOGCC_File_Downloads.py", line 71, in <module>
    GetCompletions('api.txt')
  File "C:\Users\toliver\AppData\Local\Programs\Python\Python36\WOGCC_File_Downloads.py", line 12, in __init__
    self.log.pdfpath = self.homepath / 'comppdf'
AttributeError: 'GetCompletions' object has no attribute 'log'

Does this mean I need to make the folders? When I installed Python, I selected the 'Add Path' feature. Does this have something to do with this error?

Here is the completely changed code -

import requests
from bs4 import BeautifulSoup
from pathlib import Path

class GetCompletions:
    def __init__(self, infile):
        """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.
        """
        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)



    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_pdfpath / '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.text:
                        if any(field in td.text for field in self.fields):
                            f.write('{}\n'.format(td.text))

if __name__ == '__main__':
    GetCompletions('api.txt')