starttime = re.findall("[0-9]{1,2}:[0-9]{2}\s*[aApP][mM]", time)[0] #This extracts the time, including am/pm
try:
price = bsObj.find("h3", {"class":"price-range"}).get_text().strip() # Pulls the price, which could be a price range
except: # Let's hope that it's free if it doesn't have an h3 w/ a class of "price-range"
price = "Free!"
price = price.replace("DONATIONS AT THE DOOR","Donations at the Door")
artist = bsObj.find("h1", {"class":"headliners summary"}).get_text() # Event / top artist name
artist = artist.replace("VINYL LOUNGE OPEN MIC", "Vinyl Lounge Open Mic") # Eliminate annoying all-caps, if applicable
artist = artist.replace(", VINYL LOUNGE", "") # Eliminate 'bonus' info about artist being @ Vinyl
artist = artist.replace("Gordon Sterling Presents:", "")
if "gypsy sally's jam" in artist.lower():
genre = "Potpourri"
if "closed" in artist.lower() in artist: # Skip closed private events
continue
localList = scraperLibrary.getLocalList()
if scraperLibrary.compactWord(artist) in localList:
local = "Yes"
else:
local = ""
try:
artistweb = bsObj.find("li", {"class":"web"}).find("a").attrs["href"] #THIS finds the first instance of a li with a class of "web", then digs deeper, finding the first instance w/in that li of a child a, and pulls the href. BUT - since some artists may not have link, using try/except
except:
artistweb = ""
try: # There isn't always a description...
description = bsObj.find("div", {"class":"bio"}).get_text() # Get the description, which does include a lot of breaks - will it be a mess?
except:
description = ""
[description, readmore] = scraperLibrary.descriptionTrim(description, [], 800, artistweb, newhtml)
descriptionJammed = description.replace(" ","") # Create a string with no spaces
'%Y-%m-%d').weekday() == 3:
mrHenrys.genre = "Americana" #Mr. Henry's almost always has Americana on Thursdays...
else:
mrHenrys.genre = "Jazz & Blues"
pageanddate.add(
(newPage, mrHenrys.date, datetoday)
) # Add link to list, paired with event date and today's date
mrHenrys.artist = bsObj.find(
"h1", {
"class": "tribe-events-single-event-title"
}).get_text().strip()
if mrHenrys.artist == "Smith Jackson":
mrHenrys.artist = "SmithJackson"
mrHenrys.artist = mrHenrys.artist.replace("Double Header", "")
localList = scraperLibrary.getLocalList()
if scraperLibrary.compactWord(mrHenrys.artist) in localList:
mrHenrys.local = "Yes"
else:
mrHenrys.local = ""
longtime = bsObj.find("span", {
"class": "tribe-event-date-start"
}).get_text().strip()
starttime = re.findall("[0-9]{1,2}\:[0-5][0-9]\s[aApP][mM]",
longtime)[0]
if starttime == "6:00 pm": # events with 6:00 start time actually have 6:00 doors but 2 different event times
mrHenrys.starttime = ["7:30 pm", "9:45 pm"]
else:
mrHenrys.starttime = [starttime]
try: # Most events are free, but 1 or 2 events a month require tickets
mrHenrys.price = bsObj.find("span", {