Jukebox/jukebox-software
10
0
Fork 0
Code Issues 3 Pull Requests Packages Projects Releases 2 Wiki Activity

Update parsing and stuff

Browse Source
This commit is contained in:
Cole Deck 2024-03-01 19:25:01 -06:00
parent fe5de4e54c
commit 50bf835d13
5 changed files with 110 additions and 66 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
config.yml
View File

@ -32,13 +32,13 @@ led:
ledstart: 288 ledstart: 288
ledend: 431 ledend: 431
mode: rgb mode: rgb
- universe: 1 - universe: 4
ip: 192.168.68.130 ip: 192.168.5.40
ledstart: 432 ledstart: 432
ledend: 575 ledend: 575
mode: rgb mode: rgb
- universe: 4 - universe: 1
ip: 192.168.68.131 ip: 192.168.5.4
ledstart: 576 ledstart: 576
ledend: 719 ledend: 719
mode: rgb mode: rgb

112
get_specs.py
View File

@ -26,7 +26,7 @@ def check_internet(url='https://belden.com', timeout=5):
def query_search(partnum): def query_search(partnum, source):
"""token_url = "https://www.belden.com/coveo/rest/token?t=" + str(int(time.time())) """token_url = "https://www.belden.com/coveo/rest/token?t=" + str(int(time.time()))
with requests.get(token_url) as r: with requests.get(token_url) as r:
out = json.loads(r.content) out = json.loads(r.content)
@ -49,15 +49,50 @@ def query_search(partnum):
# Bash script uses some crazy json formatting that I could not figure out # Bash script uses some crazy json formatting that I could not figure out
# Despite the fact that I wrote it # Despite the fact that I wrote it
# So I'll just leave it, becuase it works. # So I'll just leave it, becuase it works.
if source == "Belden":
command = ["./query-search.sh", partnum]
result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
if result.returncode != 0: # error
fprint("No results found in search database for " + partnum + ". No hi-res part image available.", result.stderr)
return False
else:
data_out = json.loads(result.stdout)
return data_out
elif source == "Alphawire":
alphaurl = "https://www.alphawire.com//sxa/search/results/?l=en&s={4A774076-6068-460C-9CC6-A2D8E85E407F}&itemid={BF82F58C-EFD9-4D8B-AE3E-097DD12CF7DA}&sig=&autoFireSearch=true&productpartnumber=*" + partnum + "*&v={B22CD56D-AB95-4048-8AA1-5BBDF2F2D17F}&p=10&e=0&o=ProductPartNumber%2CAscending"
r = requests.get(url=alphaurl)
data = r.json()
output = dict()
#print(data)
try:
if data["Count"] > 0:
print(data["Results"][0]["Url"])
result = data["Results"][0]
if result["Url"].split("/")[-1] == partnum:
#print(partnum)
print(result["Html"])
try:
imgidx = result["Html"].index("<img src=") + 10
imgidx2 = result["Html"].index("?", imgidx)
output["image"] = result["Html"][imgidx:imgidx2]
if output["image"].index("http") != 0:
output["image"] = ""
print("No cable image found.")
except:
print("No cable image found.")
command = ["./query-search.sh", partnum] dsidx = result["Html"].index("<a href=\"/disteAPI/") + 9
result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True) dsidx2 = result["Html"].index(partnum, dsidx) + len(partnum)
if result.returncode != 0: # error output["datasheet"] = "https://www.alphawire.com" + result["Html"][dsidx:dsidx2]
fprint("No results found in search database for " + partnum + ". No hi-res part image available.", result.stderr) #"test".index()
print(output)
return output
except:
return False
return False return False
else:
data_out = json.loads(result.stdout)
return data_out
def touch(path): def touch(path):
with open(path, 'a'): with open(path, 'a'):
@ -126,7 +161,7 @@ def get_multi(partnums):
sys.exit() sys.exit()
def _download_image(url, output_dir): # Download datasheet with known URL def _download_image(url, output_dir): # Download image with known URL
global bartext global bartext
#fprint(url) #fprint(url)
@ -151,25 +186,31 @@ def get_multi(partnums):
os.remove(partnum + "/datasheet.pdf") os.remove(partnum + "/datasheet.pdf")
sys.exit() sys.exit()
def __use_cached_datasheet(partnum, path, output_dir): def __use_cached_datasheet(partnum, path, output_dir, dstype):
fprint("Using cached datasheet for " + partnum) fprint("Using cached datasheet for " + partnum)
bar.text = "Using cached datasheet for " + partnum bar.text = "Using cached datasheet for " + partnum
bar(skipped=True) bar(skipped=True)
fprint("Parsing Datasheet contents of " + partnum) fprint("Parsing Datasheet contents of " + partnum)
bar.text = "Parsing Datasheet contents of " + partnum + ".pdf..." bar.text = "Parsing Datasheet contents of " + partnum + ".pdf..."
read_datasheet.parse(path, output_dir, partnum) read_datasheet.parse(path, output_dir, partnum, dstype)
bar(skipped=False) bar(skipped=False)
def __downloaded_datasheet(partnum, path, output_dir): def __downloaded_datasheet(partnum, path, output_dir, dstype):
fprint("Downloaded " + path) fprint("Downloaded " + path)
bar.text = "Downloaded " + path bar.text = "Downloaded " + path
bar(skipped=False) bar(skipped=False)
fprint("Parsing Datasheet contents of " + partnum) fprint("Parsing Datasheet contents of " + partnum)
bar.text = "Parsing Datasheet contents of " + partnum + ".pdf..." bar.text = "Parsing Datasheet contents of " + partnum + ".pdf..."
read_datasheet.parse(path, output_dir, partnum) read_datasheet.parse(path, output_dir, partnum, dstype)
bar(skipped=False) bar(skipped=False)
for partnum in partnums: for fullpartnum in partnums:
if fullpartnum[0:2] == "BL": # catalog.belden.com entry\
partnum = fullpartnum[2:]
dstype = "Belden"
elif fullpartnum[0:2] == "AW":
partnum = fullpartnum[2:]
dstype = "Alphawire"
output_dir = "cables/" + partnum output_dir = "cables/" + partnum
path = output_dir + "/datasheet.pdf" path = output_dir + "/datasheet.pdf"
bartext = "Downloading files for part " + partnum bartext = "Downloading files for part " + partnum
@ -177,7 +218,7 @@ def get_multi(partnums):
# #
if (not os.path.exists(output_dir + "/found_part_hires")) or not (os.path.exists(path) and os.path.getsize(path) > 1): if (not os.path.exists(output_dir + "/found_part_hires")) or not (os.path.exists(path) and os.path.getsize(path) > 1):
# Use query # Use query
search_result = query_search(partnum.replace(" ", "")) search_result = query_search(partnum.replace(" ", ""), dstype)
# Try to use belden.com search # Try to use belden.com search
if search_result is not False: if search_result is not False:
# Download high resolution part image if available and needed # Download high resolution part image if available and needed
@ -190,17 +231,17 @@ def get_multi(partnums):
# Download datasheet from provided URL if needed # Download datasheet from provided URL if needed
if os.path.exists(path) and os.path.getsize(path) > 1: if os.path.exists(path) and os.path.getsize(path) > 1:
__use_cached_datasheet(partnum, path, output_dir) __use_cached_datasheet(partnum, path, output_dir, dstype)
elif _download_datasheet(search_result["datasheet"], output_dir) is not False: elif _download_datasheet(search_result["datasheet"], output_dir) is not False:
__downloaded_datasheet(partnum, path, output_dir) __downloaded_datasheet(partnum, path, output_dir, dstype)
elif os.path.exists(path) and os.path.getsize(path) > 1: elif os.path.exists(path) and os.path.getsize(path) > 1:
__use_cached_datasheet(partnum, path, output_dir) __use_cached_datasheet(partnum, path, output_dir, dstype)
# If search fails, and we don't already have the datasheet, guess datasheet URL and skip the hires image download # If search fails, and we don't already have the datasheet, guess datasheet URL and skip the hires image download
elif _try_download_datasheet(partnum, output_dir) is not False: elif _try_download_datasheet(partnum, output_dir) is not False:
__downloaded_datasheet(partnum, path, output_dir) __downloaded_datasheet(partnum, path, output_dir, dstype)
# Failed to download with search or guess :( # Failed to download with search or guess :(
else: else:
@ -213,7 +254,7 @@ def get_multi(partnums):
# We already have a hi-res image and the datasheet - perfect! # We already have a hi-res image and the datasheet - perfect!
else: else:
fprint("Using cached hi-res part image for " + partnum) fprint("Using cached hi-res part image for " + partnum)
__use_cached_datasheet(partnum, path, output_dir) __use_cached_datasheet(partnum, path, output_dir, dstype)
if len(failed) > 0: if len(failed) > 0:
fprint("Failed to download:") fprint("Failed to download:")
@ -227,21 +268,22 @@ def get_multi(partnums):
if __name__ == "__main__": if __name__ == "__main__":
partnums = ["7958A", "10GXS12", "RST 5L-RKT 5L-949", partnums = ["AW3248", "BL7958A", "BL10GXS12", "BLRST 5L-RKT 5L-949",
"10GXS13", "BL10GXS13",
"10GXW12", "BL10GXW12",
"10GXW13", "BL10GXW13",
"2412", "BL2412",
"2413", "BL2413",
"OSP6AU", "BLOSP6AU",
"FI4D024P9", "BLFI4D024P9",
"FISD012R9", "BLFISD012R9",
"FDSD012A9", "BLFDSD012A9",
"FSSL024NG", "BLFSSL024NG",
"FISX006W0", "BLFISX006W0",
"FISX00103", "BLFISX00103",
"C6D1100007" "BLC6D1100007"
] ]
get_multi(partnums) #get_multi(partnums)
query_search("3248", "Alphawire")

6
led_control.py
View File

@ -178,9 +178,9 @@ def init():
sendall(data) sendall(data)
#time.sleep(50000) #time.sleep(50000)
fprint("Running start-up test sequence...") fprint("Running start-up test sequence...")
for y in range(1): for y in range(100):
for x in range(len(leds)): for x in range(len(leds)):
setpixel(5,5,5,x) setpixel(0,0,150,x)
sendall(data) sendall(data)
#time.sleep(2) #time.sleep(2)
#alloffsmooth() #alloffsmooth()
@ -290,7 +290,7 @@ def close():
time.sleep(0.5) time.sleep(0.5)
sender.stop() sender.stop()
def mapimage(image, fps=60): def mapimage(image, fps=90):
global start global start
while uptime() - start < 1/fps: while uptime() - start < 1/fps:
time.sleep(0.00001) time.sleep(0.00001)

BIN
map.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 381 KiB

After

Width:  |  Height:  |  Size: 381 KiB

50
read_datasheet.py
View File

@ -12,7 +12,7 @@ from util import fprint
import uuid import uuid
from util import run_cmd from util import run_cmd
def parse(filename, output_dir, partnum): def parse(filename, output_dir, partnum, dstype):
# Extract table data # Extract table data
@ -24,6 +24,7 @@ def parse(filename, output_dir, partnum):
page = reader.pages[0] page = reader.pages[0]
table_list = {} table_list = {}
for table in tables: for table in tables:
table.df.infer_objects(copy=False)
table.df.replace('', np.nan, inplace=True) table.df.replace('', np.nan, inplace=True)
table.df.dropna(inplace=True, how="all") table.df.dropna(inplace=True, how="all")
table.df.dropna(inplace=True, axis="columns", how="all") table.df.dropna(inplace=True, axis="columns", how="all")
@ -139,29 +140,30 @@ def parse(filename, output_dir, partnum):
# multi-page table check # multi-page table check
if table_name.isdigit() and len(tables) > 1: if dstype == "Belden":
fprint(table_name) if table_name.isdigit() and len(tables) > 1:
fprint(previous_table) fprint(table_name)
fprint(previous_table)
main_key = previous_table
cont_key = table_name main_key = previous_table
fprint(tables) cont_key = table_name
if vertical == False: fprint(tables)
main_keys = list(tables[main_key].keys()) if vertical == False:
for i, (cont_key, cont_values) in enumerate(tables[cont_key].items()): main_keys = list(tables[main_key].keys())
if i < len(main_keys): for i, (cont_key, cont_values) in enumerate(tables[cont_key].items()):
fprint(tables[main_key][main_keys[i]]) if i < len(main_keys):
tables[main_key][main_keys[i]] = (tables[main_key][main_keys[i]] + (cont_key,) + cont_values) fprint(tables[main_key][main_keys[i]])
tables[main_key][main_keys[i]] = (tables[main_key][main_keys[i]] + (cont_key,) + cont_values)
del tables[table_name]
del tables[table_name]
else:
for key in tables[cont_key].keys(): else:
tables[main_key][key] = tables[cont_key][key] for key in tables[cont_key].keys():
del tables[table_name] tables[main_key][key] = tables[cont_key][key]
del tables[table_name]
previous_table = table_name previous_table = table_name