def beatportSearch(filename, track, artistVariations, titleVariations, headers, search, webScrapingWindow, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, labelFrame, searchFrame, pageFrame, componentFrame, audio, options, initialCounter, imageCounter, images):
global count
count = 0
widgetList = allWidgets(searchFrame)
for item in widgetList: item.pack_forget()
if len(filename) > 60: tk.Label(searchFrame, text="\nSearching Beatport for " + str(filename)[0:59] + "...", font=("Proxima Nova Rg", 13), fg="white", bg=bg).pack(side="left", padx=(10, 0), anchor='w')
else: tk.Label(searchFrame, text="\nSearching Beatport for " + str(filename), font=("Proxima Nova Rg", 13), fg="white", bg=bg).pack(side="left", padx=(10, 0), anchor='w')
leftComponentFrame, rightComponentFrame = resetLeftRightFrames(componentFrame)
refresh(webScrapingWindow)
url = "https://www.google.co.in/search?q=" + search + " Beatport"
soup = prepareRequest(url, headers, webScrapingWindow, leftComponentFrame)
if soup == False:
Label(leftComponentFrame, text="Connection Failure", font=("Proxima Nova Rg", 11), fg="white", bg=bg).pack(anchor='w')
refresh(webScrapingWindow)
return track, imageCounter, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, searchFrame, pageFrame, componentFrame
for link in soup.find_all('a'):
if "www.beatport.com" in link.get('href').split('&')[0]:
mismatch = True
resultString = str(link).lower()
for variation in titleVariations:
if variation in resultString:
mismatch = False
break
if not mismatch:
link = link.get('href').split('&')[0].split('=')[1]
if "remix" in link and "remix" in track.title.lower() or "remix" not in track.title.lower() and "remix" not in link:
# clear component frames of existing content
widgetList = allWidgets(componentFrame)
for item in widgetList: item.pack_forget()
widgetList = allWidgets(pageFrame)
for item in widgetList: item.pack_forget()
webScrapingPage += 1
leftComponentFrame, rightComponentFrame = resetLeftRightFrames(componentFrame)
# page counter and navigation buttons
rerenderControls(pageFrame, webScrapingPage)
if len(link) > 75: label = tk.Label(leftComponentFrame, text="\n" + str(link)[0:74] + "...", cursor="hand2", font=("Proxima Nova Rg", 11), fg="white", bg=bg)
else: label = tk.Label(leftComponentFrame, text="\n" + str(link), cursor="hand2", font=("Proxima Nova Rg", 11), fg="white", bg=bg)
label.bind("<Button-1>", lambda e, link=link: webbrowser.open_new(link))
label.pack(padx=(10, 0), pady=(0, 25), anchor='w')
webScrapingLeftPane[webScrapingPage] = leftComponentFrame
# assume match will fail and no image will be found
webScrapingRightPane[webScrapingPage] = "NA"
webScrapingLinks[webScrapingPage] = link
refresh(webScrapingWindow)
soup = prepareRequest(link, headers, webScrapingWindow, leftComponentFrame)
if soup != False and "Oops... the page you were looking for could not be found" not in str(soup):
# check if page is a track (single) or a release (album)
# case 1: release
if link[25:32] == "release": imageCounter, images, webScrapingLeftPane, webScrapingRightPane = beatportRelease(soup, titleVariations, track, headers, audio, leftComponentFrame, rightComponentFrame, webScrapingWindow, webScrapingLeftPane, webScrapingRightPane, webScrapingPage, options, initialCounter, imageCounter, images)
# case 2: track
elif link[25:30] == "track": imageCounter, images, webScrapingLeftPane, webScrapingRightPane = beatportTrack(soup, track, headers, audio, leftComponentFrame, rightComponentFrame, webScrapingWindow, webScrapingLeftPane, webScrapingRightPane, webScrapingPage, options, initialCounter, imageCounter, images)
else: tk.Label(leftComponentFrame, text="Track failed due to dead link or territory restriction", font=("Proxima Nova Rg", 11), fg="white", bg=bg).pack(padx=(10, 0), pady=(5, 0), anchor='w')
if options['Limit Number of Matches per Site (B)'].get() and count >= options['Match Limit (I)'].get(): break
return track, imageCounter, images, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, searchFrame, pageFrame, componentFrame
def searchQuery(track, result, headers, webScrapingWindow, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, pageFrame, leftComponentFrame, componentFrame, artistVariations, titleVariations, audio, options, initialCounter, imageCounter, images):
link = str(result.find('a').get('href')).split('&')[0].split('=')[1]
soup = prepareRequest(link, headers, webScrapingWindow, leftComponentFrame)
if soup != False:
# first check if the title is in the tracklist, push data if it is
link = soup.find('table', class_="playlist")
# handle 404 links
if link != None:
# post link to web scraping window
widgetList = allWidgets(componentFrame)
for item in widgetList: item.pack_forget()
widgetList = allWidgets(pageFrame)
for item in widgetList: item.pack_forget()
webScrapingPage += 1
leftComponentFrame, rightComponentFrame = resetLeftRightFrames(componentFrame)
# page counter and navigation buttons
rerenderControls(pageFrame, webScrapingPage)
weblink = str(result.find('a').get('href')).split('&')[0].split('=')[1]
label = tk.Label(leftComponentFrame, text="\n" + str(weblink), cursor="hand2", font=("Proxima Nova Rg", 11), fg="white", bg=bg)
label.bind("<Button-1>", lambda e, link=weblink: webbrowser.open_new(link))
label.pack(padx=(10, 0), pady=(0, 25), anchor="w")
webScrapingLeftPane[webScrapingPage] = leftComponentFrame
webScrapingRightPane[webScrapingPage] = "NA"
webScrapingLinks[webScrapingPage] = weblink
refresh(webScrapingWindow)
finalMatch = False
# artist + title format
if link.find('td', class_="track tracklist_track_title mini_playlist_track_has_artist")!=None:
# first entry goes by different class name
temp = link.find('tr', class_='first tracklist_track track')
if temp != None: finalMatch, imageCounter, images, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage = artistTitleSearch(temp, artistVariations, titleVariations, audio, soup, track, headers, webScrapingWindow, webScrapingLeftPane, webScrapingRightPane, webScrapingPage, webScrapingLinks, leftComponentFrame, rightComponentFrame, options, initialCounter, imageCounter, images)
# remaining entries
if not finalMatch:
for temp in link.find_all('tr', class_="tracklist_track track"):
finalMatch, imageCounter, images, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage = artistTitleSearch(temp, artistVariations, titleVariations, audio, soup, track, headers, webScrapingWindow, webScrapingLeftPane, webScrapingRightPane, webScrapingPage, webScrapingLinks, leftComponentFrame, rightComponentFrame, options, initialCounter, imageCounter, images)
if finalMatch: break
# title format
elif link.find('td', class_="track tracklist_track_title")!=None:
# first entry goes by different class name
temp = link.find('tr', class_='first tracklist_track track')
if temp != None: finalMatch, imageCounter, images, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage = titleSearch(temp, titleVariations, audio, soup, track, headers, webScrapingWindow, webScrapingLeftPane, webScrapingRightPane, webScrapingPage, webScrapingLinks, leftComponentFrame, rightComponentFrame, options, initialCounter, imageCounter, images)
# remaining entries
if not finalMatch:
for temp in link.find_all('tr', class_="tracklist_track track"):
finalMatch, imageCounter, images, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage = titleSearch(temp, titleVariations, audio, soup, track, headers, webScrapingWindow, webScrapingLeftPane, webScrapingRightPane, webScrapingPage, webScrapingLinks, leftComponentFrame, rightComponentFrame, options, initialCounter, imageCounter, images)
if finalMatch: break
if not finalMatch:
tk.Label(leftComponentFrame, text="Track did not match with any of the listings", font=("Proxima Nova Rg", 11), fg="white", bg=bg).pack(padx=(10, 0), pady=(5, 0), anchor="w")
refresh(webScrapingWindow)
return imageCounter, images, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage
def discogsSearch(filename, track, artistVariations, titleVariations, headers, search, webScrapingWindow, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, labelFrame, searchFrame, pageFrame, componentFrame, audio, options, initialCounter, imageCounter, images):
global count
count = 0
widgetList = allWidgets(searchFrame)
for item in widgetList: item.pack_forget()
if len(filename) > 60: tk.Label(searchFrame, text="\nSearching Discogs for " + str(filename)[0:59] + "...", font=("Proxima Nova Rg", 13), fg="white", bg=bg).pack(side="left", padx=(10, 0), anchor='w')
else: tk.Label(searchFrame, text="\nSearching Discogs for " + str(filename), font=("Proxima Nova Rg", 13), fg="white", bg=bg).pack(side="left", padx=(10, 0), anchor='w')
leftComponentFrame, rightComponentFrame = resetLeftRightFrames(componentFrame)
refresh(webScrapingWindow)
url = "https://www.google.co.in/search?q=" + search + " Discogs"
soup = prepareRequest(url, headers, webScrapingWindow, leftComponentFrame)
if soup != False:
# result includes link and description
for result in soup.find_all('div', class_="ZINbbc xpd O9g5cc uUPGi"):
if "www.discogs.com" in str(result.find('a').get('href')).lower().split('&')[0]:
searchTitle = track.title
if ' (' in track.title and ')' in track.title: searchTitle = track.title[:track.title.index(' (')]
if searchTitle.lower() in str(result).lower(): imageCounter, images, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage = searchQuery(track, result, headers, webScrapingWindow, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, pageFrame, leftComponentFrame, componentFrame, artistVariations, titleVariations, audio, options, initialCounter, imageCounter, images)
else:
resultString = str(result).replace('-', ' ').lower()
for variation in titleVariations:
variation = variation.replace('-', ' ')
if variation.lower() in resultString:
imageCounter, images, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage = searchQuery(track, result, headers, webScrapingWindow, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, pageFrame, leftComponentFrame, componentFrame, artistVariations, titleVariations, audio, options, initialCounter, imageCounter, images)
break
if options['Limit Number of Matches per Site (B)'].get() and count >= options['Match Limit (I)'].get(): break
return track, imageCounter, images, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, searchFrame, pageFrame, componentFrame
def enableControls(searchFrame, pageFrame, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, componentFrame):
global currentPage
currentPage = webScrapingPage
# clear page frame
widgetList = allWidgets(searchFrame)
for item in widgetList: item.pack_forget()
widgetList = allWidgets(pageFrame)
for item in widgetList: item.pack_forget()
tk.Label(searchFrame, text="\nSearch Complete", font=("Proxima Nova Rg", 13), fg="white", bg=bg).pack(side="left", padx=(10, 0), anchor="w")
farRightButton = tk.Button(pageFrame, text=">>", state=DISABLED, font=("Proxima Nova Rg", 11), fg="white", bg=bg, width=2, command=lambda: navigateFarRight(leftButton, farLeftButton, rightButton, farRightButton, pageIndicator, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, componentFrame))
farRightButton.pack(side="right", padx=(5, 30))
rightButton = tk.Button(pageFrame, text=">", state=DISABLED, font=("Proxima Nova Rg", 11), fg="white", bg=bg, width=2, command=lambda: navigateRight(leftButton, farLeftButton, rightButton, farRightButton, pageIndicator, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, componentFrame))
rightButton.pack(side="right", padx=(5,5))
pageIndicator = tk.Label(pageFrame, text=str(webScrapingPage) + "/" + str(webScrapingPage), font=("Proxima Nova Rg", 11), fg="white", bg=bg, anchor='e')
pageIndicator.pack(side="right", padx=(5,5))
leftButton = tk.Button(pageFrame, text="<", font=("Proxima Nova Rg", 11), fg="white", bg=bg, width=2, command=lambda: navigateLeft(leftButton, farLeftButton, rightButton, farRightButton, pageIndicator, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, componentFrame))
farLeftButton = tk.Button(pageFrame, text="<<", font=("Proxima Nova Rg", 11), fg="white", bg=bg, width=2, command=lambda: navigateFarLeft(leftButton, farLeftButton, rightButton, farRightButton, pageIndicator, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, componentFrame))
leftButton.pack(side="right", padx=(5,5))
farLeftButton.pack(side="right", padx=(5,5))
if webScrapingPage <= 1:
leftButton.config(state=DISABLED)
farLeftButton.config(state=DISABLED)
def navigateRight(leftNavigationButton, rightNavigationButton, titleFrame,
contentFrame, imageFrame, finalTitles, finalResults,
imageSelections, imageCounter, thumbnails, pageIndicator):
global currentPage
currentPage += 1
# handle navigation frame
if currentPage == len(finalResults):
rightNavigationButton.config(state=DISABLED)
leftNavigationButton.config(state=NORMAL)
pageIndicator.config(text=str(currentPage) + "/" + str(len(finalResults)))
# rerender title, content, and image frame
widgetList = allWidgets(titleFrame)
for item in widgetList:
item.pack_forget()
widgetList = allWidgets(contentFrame)
for item in widgetList:
item.pack_forget()
widgetList = allWidgets(imageFrame)
for item in widgetList:
item.pack_forget()
tk.Label(titleFrame,
text=finalTitles[(currentPage - 1)] + "\n",
font=("Proxima Nova Rg", 11),
fg="white",
bg=bg,
bd=-10,
anchor="w").pack(side="top", anchor="w")
# remove leading newline character
tk.Label(contentFrame,
text=finalResults[(currentPage - 1)].lstrip() + '\n',
font=("Proxima Nova Rg", 11),
fg="white",
bg=bg,
justify="left",
bd=-10,
anchor="center").pack(anchor="center")
renderImage(imageFrame, imageSelections, imageCounter, thumbnails,
(currentPage - 1))
def navigateFarLeft(leftButton, farLeftButton, rightButton, farRightButton, pageIndicator, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, componentFrame):
global currentPage
currentPage=1
leftButton.config(state=DISABLED)
farLeftButton.config(state=DISABLED)
if webScrapingPage > 1:
rightButton.config(state=NORMAL)
farRightButton.config(state=NORMAL)
# rerender page indicator
pageIndicator.config(text=str(currentPage) + "/" + str(webScrapingPage))
# rerender left and right components
widgetList = allWidgets(componentFrame)
for item in widgetList: item.pack_forget()
leftComponentFrame, rightComponentFrame = resetLeftRightFrames(componentFrame)
# left component
renderLeftComponent(webScrapingLeftPane, leftComponentFrame, webScrapingLinks, currentPage)
# right component
renderRightComponent(webScrapingRightPane, rightComponentFrame, currentPage)
def navigateLeft(leftButton, farLeftButton, rightButton, farRightButton, pageIndicator, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, componentFrame):
global currentPage
currentPage -= 1
if currentPage <= 1:
leftButton.config(state=DISABLED)
farLeftButton.config(state=DISABLED)
rightButton.config(state=NORMAL)
farRightButton.config(state=NORMAL)
# rerender page indicator
pageIndicator.config(text=str(currentPage) + "/" + str(webScrapingPage))
# rerender left and right components
widgetList = allWidgets(componentFrame)
for item in widgetList: item.pack_forget()
leftComponentFrame = tk.Frame(componentFrame, bg=bg)
leftComponentFrame.pack(side="left", anchor="w", fill=Y)
rightComponentFrame = tk.Frame(componentFrame, bg=bg)
rightComponentFrame.pack(side="right", anchor="e", fill=Y)
# left component
renderLeftComponent(webScrapingLeftPane, leftComponentFrame, webScrapingLinks, currentPage)
# right component
renderRightComponent(webScrapingRightPane, rightComponentFrame, currentPage)
def junodownloadSearch(filename, track, artistVariations, titleVariations,
headers, search, webScrapingWindow, webScrapingLeftPane,
webScrapingRightPane, webScrapingLinks, webScrapingPage,
labelFrame, searchFrame, pageFrame, componentFrame,
audio, options, initialCounter, imageCounter, images):
global count
count = 0
widgetList = allWidgets(searchFrame)
for item in widgetList:
item.pack_forget()
if len(filename) > 60:
tk.Label(searchFrame,
text="\nSearching Juno Download for " + str(filename)[0:59] +
"...",
font=("Proxima Nova Rg", 13),
fg="white",
bg=bg).pack(side="left", padx=(10, 0), anchor='w')
else:
tk.Label(searchFrame,
text="\nSearching Juno Download for " + str(filename),
font=("Proxima Nova Rg", 13),
fg="white",
bg=bg).pack(side="left", padx=(10, 0), anchor='w')
leftComponentFrame, rightComponentFrame = resetLeftRightFrames(
componentFrame)
refresh(webScrapingWindow)
url = "https://www.google.co.in/search?q=" + search + " Junodownload"
soup = prepareRequest(url, headers, webScrapingWindow, leftComponentFrame)
if soup != False:
for result in soup.find_all('div', class_="ZINbbc xpd O9g5cc uUPGi"):
if 'junodownload.com' and 'products' in result.find('a').get(
'href').split('&')[0].lower():
resultString = str(result).replace('&', 'and').lower()
for variation in titleVariations:
variation = variation.replace('-', ' ')
if variation.lower() in resultString:
link = result.find('a').get('href').split('&')[0][7:]
refresh(webScrapingWindow)
soup = prepareRequest(link, headers, webScrapingWindow,
leftComponentFrame)
if soup != False:
# post link to web scraping window
widgetList = allWidgets(componentFrame)
for widget in widgetList:
widget.pack_forget()
widgetList = allWidgets(pageFrame)
for widget in widgetList:
widget.pack_forget()
# increment web scraping page and rerender count
webScrapingPage += 1
leftComponentFrame, rightComponentFrame = resetLeftRightFrames(
componentFrame)
rerenderControls(pageFrame, webScrapingPage)
if len(link) >= 75:
label = tk.Label(leftComponentFrame,
text="\n" + str(link)[0:74] +
"...",
cursor="hand2",
font=("Proxima Nova Rg", 11),
fg="white",
bg=bg)
else:
label = tk.Label(leftComponentFrame,
text="\n" + str(link),
cursor="hand2",
font=("Proxima Nova Rg", 11),
fg="white",
bg=bg)
label.bind(
"<Button-1>",
lambda e, link=link: webbrowser.open_new(link))
label.pack(padx=(10, 0), pady=(0, 25), anchor='w')
# update left component history frame
webScrapingLeftPane[
webScrapingPage] = leftComponentFrame
# assume match will fail and no image will be found
webScrapingRightPane[webScrapingPage] = "NA"
# update link
webScrapingLinks[webScrapingPage] = link
finalMatch = False
# search individual listings in table
for item in soup.find_all(
'div',
class_=
"row gutters-sm align-items-center product-tracklist-track"
):
name = item.find('span').get_text()
if ' - ' in name:
trackArtist = item.find(
'span').get_text().split(' - ')[0]
trackTitle = item.find(
'span').get_text().split(' - ')[1]
else:
trackArtist = ''
trackTitle = item.find('span').get_text()
if not compareTokens(variation, trackTitle):
# check runtime to ensure track is correct
runtime = item.find(
'div',
class_=
"col-1 d-none d-lg-block text-center"
).get_text()
if not compareRuntime(runtime, audio):
count += 1
finalMatch = True
for value in item.find_all(
'div',
class_=
"col-1 d-none d-lg-block text-center"
):
# extract BPM
if ":" not in value.get_text(
) and value.get_text(
) != '\xa0' and "BPM" in options[
"Selected Tags (L)"]:
BPM = value.get_text()
tk.Label(
leftComponentFrame,
text="BPM: " + str(BPM),
font=("Proxima Nova Rg",
11),
fg="white",
bg=bg).pack(padx=(10, 0),
pady=(5, 0),
anchor='w')
webScrapingLeftPane[
webScrapingPage] = leftComponentFrame
refresh(webScrapingWindow)
track.BPMList.append(int(BPM))
track.BPMList.append(int(BPM))
# only push release and genre from header if title is found in tracklist
for data in soup.select(
'div[class=mb-3]'):
# extract release date
if "Release_Date" in options[
"Selected Tags (L)"]:
release = data.find(
"span",
itemprop="datePublished"
).get_text()
tk.Label(
leftComponentFrame,
text="Year: " +
str(release),
font=("Proxima Nova Rg",
11),
fg="white",
bg=bg).pack(padx=(10, 0),
pady=(5, 0),
anchor='w')
track.yearList.append(
int(release[-4:]))
# extract genre
if "Genre" in options[
"Selected Tags (L)"]:
genre = data.find(
"a").get_text()
tk.Label(
leftComponentFrame,
text="Genre: " +
str(genre),
font=("Proxima Nova Rg",
11),
fg="white",
bg=bg).pack(padx=(10, 0),
pady=(5, 0),
anchor='w')
track.genreList.append(genre)
webScrapingLeftPane[
webScrapingPage] = leftComponentFrame
# extract image
if options[
"Extract Image from Website (B)"].get(
) == True and track.stop == False:
try:
item = soup.find(
'div', class_="jw-page")
item = item.find('img').get(
'data-src-full')
# write junodownload image to drive
with open(
resource_path(
'Temp/' +
str(imageCounter) +
'.jpg'),
"wb") as file:
file.write(
requests.get(
item,
headers=headers).
content)
track.URLList.append(item)
# load file icon
fileImageImport = Image.open(
resource_path(
'Temp/' +
str(imageCounter) +
'.jpg'))
width, height = fileImageImport.size
fileImageImport = fileImageImport.resize(
(200, 200),
Image.ANTIALIAS)
images.append([
fileImageImport, width,
height
])
photo = ImageTk.PhotoImage(
fileImageImport)
fileImage = tk.Label(
rightComponentFrame,
image=photo,
bg=bg)
fileImage.image = photo
fileImage.pack(padx=(0, 100),
anchor="e")
imageCounter += 1
refresh(webScrapingWindow)
webScrapingRightPane[
webScrapingPage] = rightComponentFrame
# perform image scraping if enabled in options
if options[
"Reverse Image Search (B)"].get(
) == True and not track.stop:
if not performSearch(
initialCounter,
imageCounter):
imageCounter, images, track = reverseImageSearch(
item, headers,
imageCounter,
images, track,
options)
except:
pass
# avoid counting the same entry twice
if not finalMatch:
tk.Label(
leftComponentFrame,
text=
"Track did not match with any of the listings",
font=("Proxima Nova Rg", 11),
fg="white",
bg=bg).pack(padx=(10, 0),
pady=(5, 0),
anchor="w")
refresh(webScrapingWindow)
break
if options['Limit Number of Matches per Site (B)'].get(
) and count >= options['Match Limit (I)'].get():
break
return track, imageCounter, images, webScrapingLeftPane, webScrapingRightPane, webScrapingLinks, webScrapingPage, searchFrame, pageFrame, componentFrame