adding "na" text to an array within a loop - python-3.x

I've gotten all the data I wanted from scraping this metacritc url (see below) however, I can't seem to put a value in for when I don't find the associated value for list (missing values)
I would like to have it so all the lists are even (so I can right to .csv)
Here is the code I have so far:
from requests import get
from bs4 import BeautifulSoup
from urllib.request import Request, urlopen
import pandas as pd
#Define year
year_number = 2018
# Define the URL
i = range(0, 1)
names = []
metascores = []
userscores = []
userscoresNew = []
release_dates = []
release_datesNew = []
publishers = []
ratings = []
genres = []
genresNew = []
for element in i:
url = "http://www.metacritic.com/browse/games/score/metascore/year/pc/filtered?view=detailed&sort=desc&year_selected=" + format(year_number)
print(url)
year_number -= 1
# not sure about this but it works (I was getting blocked by something and this the way I found around it)
req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})
web_byte = urlopen(req).read()
webpage = web_byte.decode('utf-8')
#this grabs the all the text from the page
html_soup = BeautifulSoup(webpage, 'html5lib')
#this is for selecting all the games in from 1 to 100 (the list of them)
game_names = html_soup.find_all("div", class_="main_stats")
game_metas = html_soup.find_all("a", class_="basic_stat product_score")
game_users = html_soup.find_all("li", class_='stat product_avguserscore')
game_releases = html_soup.find_all("ul", class_='more_stats')
game_publishers = html_soup.find_all("li", class_='stat publisher')
game_ratings = html_soup.find_all("li", class_='stat maturity_rating')
game_genres = html_soup.find_all("li", class_='stat genre')
#Extract data from each game
for games in game_names:
name = games.find()
names.append(name.text.strip())
for games2 in game_metas:
metascore = games2.find()
metascores.append(metascore.text.strip())
for games3 in game_releases:
release_date = games3.find()
release_dates.append(release_date.text.strip())
for games4 in game_users:
userscore = games4.find('span', class_="data textscore textscore_favorable") or games4.find('span', class_="data textscore textscore_mixed")
if userscore:
userscores.append(userscore.text)
for games5 in game_publishers:
publisher = games5.find("span", class_ = "data")
if publisher:
publishers.append(publisher.text)
for games6 in game_ratings:
rating = games6.find("span", class_ = "data")
for games7 in game_genres:
genre = games7.find("span", class_ = "data")
if genre:
genres.append(genre.text)
for x in release_dates:
temp = str(x)
temp2 = temp.replace("Release Date:\n ", "")
release_datesNew.append(temp2)
for z in genres:
temp3 = str(z)
temp4 = temp3.strip()
temp5 = temp4.replace(" ", "")
genresNew.append(temp5)
df = pd.DataFrame({'Games:': names})
not sure how I would work that in to this code
From what I understand it's take all the data it can find but if there is a blank it doesn't know about it
can someone adivse the best solution for this situation
any help would be great
Thanks

Just add else's for the existing conditions...
if userscore:
userscores.append(userscore.text)
else:
userscores.append('na')

Related

Split function doesnt work for string and for list

Just doing one of my first web scraping and I already have elements I wanted to extract but I cannot find the function to print them as a numbered list. The code I have for now:
r = requests.get('https://mmazurek.dev/category/programowanie-2/page/3/', proxies={'http':'82.119.170.106'})
page = soup(r.content, "html.parser")
contents=page.findAll(None, class_="post-title-link")
for content in contents:
text_content=list(content.get_text())
first_letter=str(text_content[0])
x="".join(first_letter)
listToStr = "".join(map(str, text_content))
print(listToStr)
The purpose is to have list printed like:
P....
J...
...
Hope you dont mind it's a Polish text;)
def get_html(url, useragent=None, proxy=None):
session = requests.Session()
request = session.get(url=url, headers=useragent, proxies=proxy)
if request.status_code == 200:
soup = bs(request.text, 'lxml')
return soup
else:
print("Error " + str(request.status_code))
return request.status_code
def parse(soup):
data = []
contents = soup.findAll(None, class_="post-title-link")
for i, content in enumerate(contents):
text = content.text
href = content['href']
data.append([
i,
text,
href,
])
return data
return data
data = parse(get_html('https://mmazurek.dev/category/programowanie-2/page/3/', proxy={'http': '82.119.170.106'}))
print(data)

Unable to scrape all data

from bs4 import BeautifulSoup
import requests , sys ,os
import pandas as pd
URL = r"https://www.vault.com/best-companies-to-work-for/law/top-100-law-firms-rankings/year/"
My_list = ['2007','2008','2009','2010','2011','2012','2013','2014','2015','2016','2017','2018','2019','2020']
Year= []
CompanyName = []
Rank = []
Score = []
print('\n>>Process started please wait\n\n')
for I, Page in enumerate(My_list, start=1):
url = r'https://www.vault.com/best-companies-to-work-for/law/top-100-law-firms-rankings/year/{}'.format(Page)
print('\nData fetching from : ',url)
Res = requests.get(url)
soup = BeautifulSoup(Res.content , 'html.parser')
data = soup.find('section',{'class': 'search-result CompanyWorkfor RankingMain FindSchools school-results contrastSection d-flex justify-content-center min-height Rankings CompRank'})
if len(soup) > 0:
print("\n>>Getting page source for :" , url)
else:
print("Please Check url :",url)
for i, item in enumerate(data.find_all("div", {"class": "RankItem"})):
year = item.find("i",{"class":"fa-stack fa-2x"})
Year.append(year)
title = item.find("h3", {"class": "MainLink"}).get_text().strip()
CompanyName.append(title)
rank = item.find("div", {"class": "RankNumber"}).get_text().strip()
Rank.append(rank)
score = item.find("div", {"class": "score"}).get_text().strip()
Score.append(score)
Data = pd.DataFrame({"Year":Year,"CompanyName":CompanyName,"Rank":Rank,"Score":Score})
Data[['First','Score']] = Data.Score.str.split(" " , expand =True,)
Data[['hash','Rank']] = Data.Rank.str.split("#" , expand = True,)
Data.drop(columns = ['hash','First'],inplace = True)
Data.to_csv('Vault_scrap.csv',index = False)
For each url the expected output Data for year, rank, title and score is 100 lines, but I'm getting only 10 lines.
You can iterate through the year and pages like this.
import requests
import pandas as pd
url = 'https://www.vault.com/vault/api/Rankings/LoadMoreCompanyRanksJSON'
def page_loop(year, url):
tableReturn = pd.DataFrame()
for page in range(1,101):
payload = {
'rank': '2',
'year': year,
'category': 'LBACCompany',
'pg': page}
jsonData = requests.get(url, params=payload).json()
if jsonData == []:
return tableReturn
else:
print ('page: %s' %page)
tableReturn = tableReturn.append(pd.DataFrame(jsonData), sort=True).reset_index(drop=True)
return tableReturn
results = pd.DataFrame()
for year in range(2007,2021):
print ("\n>>Getting page source for :" , year)
jsonData = page_loop(year, url)
results = results.append(pd.DataFrame(jsonData), sort=True).reset_index(drop=True)

IndexError at /new-watch-hour-graph/

def getNewWatchedCountGraph(requests):
data = Video.getNewWatchedCountGraph(requests)
data = json.loads(data)
# print(data)
x = []
m = []
bg = {}
res = {}
monthnumbers = []
currentMonth = datetime.datetime.now().month
for item in data:
seconds = int(item['count'])
x.append(seconds)
mydate = datetime.datetime.strptime(item['_id'], "%Y-%m")
monthnumbers.append(mydate.month)
m.append(mydate.strftime("%B"))
startMonths = monthnumbers[0] #line 116
endMonths = currentMonth+1
data = []
mon = []
for months in range(startMonths,endMonths):
if months not in monthnumbers:
mon.append(calendar.month_name[months])
data.append(0)
else:
mon.append(calendar.month_name[months])
monthIndex = monthnumbers.index(months)
data.append(x[monthIndex])
res['series_name'] = "Views"
res['series'] = list(data)
res['xdata'] = list(mon)
restrn_response = dumps(res)
return HttpResponse(restrn_response)
I have made this function to show the graph of total number of views.
It is working fine in my local server. But showing List index out of range in main server at line no 116. Where am i doing wrong?
This happens because monthnumbers is empty. Given that it’s being filled while iterating over data, I think the loop doesn’t even start because data is empty.

I'm stumped at looping through a returned list of URLs

My first python project, I'm trying to scrape restaurant inspection. One site has summaries that offer keys to the detailed reports that I want to scrape. I'm stumped at looping through the keyed list of urls to get the details.
import pandas as pd
import bs4
import datetime
import re
import lxml
from urllib.request import urlopen
from urllib.error import HTTPError
try:
insp = pd.read_csv("ftp://dbprftp.state.fl.us/pub/llweb/5fdinspi.csv",
usecols=[2,14,18,80,81])
except IOError:
print("The file is not accessible.")
insp.columns = ["CountyName", "InspectDate",
"NumHighVio", "LicenseID", "VisitID"]
# filter for alachua county restaurants
alachua = insp[insp.CountyName == 'Alachua']
# filter for restaurants that had at least one serious violation
alachua = alachua[alachua.NumHighVio > 0]
# change date string to date object
alachua['InspectDate'] = pd.to_datetime(alachua['InspectDate'])
# sort most recent
alachua = alachua.sort_values('InspectDate', ascending=False)
# prefer to have user set timedelta below:
today = pd.to_datetime('today')
startDay = datetime.date.today() - datetime.timedelta(days=30)
alachua = alachua[(alachua['InspectDate'] > startDay) &
(alachua['InspectDate'] < today)]
# takes LicenseID and VisitID, passes it into the urls for detailed reports
for index, rows in alachua.iterrows():
visitID = rows['VisitID']
licID = rows['LicenseID']
urls = "https://www.myfloridalicense.com/inspectionDetail.asp?InspVisitID=
%s &licid= %s" % (visitID, licID)
urls = urls.replace(' ', '')
print(urls)
## here's my problem:
for url in urls:
def get_inspect_detail():
html = urlopen(url)
soup = bs4.BeautifulSoup(html.read(), 'lxml')
details = soup.find_all('font', {'face':'verdana'})[10:]
for detail in details:
siteName = details[0].text
licNum = details[2].text
siteRank = details[4].text
expDate = details[6].text
primeStatus = details[8].text
secStatus = details[10].text
siteAddress = details[12].text
inspectResult = details[20].text
observed1 = details[34].get_text
observed2 = details[36].text
observed3 = details[38].text
observed4 = details[40].text
observed5 = details[42].text
observed6 = details[44].text
observed7 = details[46].text
observed8 = details[48].text
observed9 = details[50].text
observed10 = details[52].text
detailsLib = {
'Restaurant': siteName,
'License': licNum,
'Rank': siteRank,
'Expires': expDate,
'Primary': primeStatus,
'Secondary': secStatus,
'Address': siteAddress,
'Result': inspectResult,
'Observed1': observed1,
'Observed2': observed2,
'Observed3': observed3,
'Observed4': observed4,
'Observed5': observed5,
'Observed6': observed6,
'Observed7': observed7,
'Observed8': observed8,
'Observed9': observed9,
'Observed10': observed10
}
repr(get_inspect_detail())
Probably an obvious mistake or lack of knowledge, but I can get the unscrubbed data for one url, but not for all.
I dont see a reason to define your function inside the loop. You would end up with a lot of redundant definitions this way. Second, you could just define a result list and accumulate the detailsLib objects inside it.
def get_inspect_detail(url):
html = urlopen(url)
soup = bs4.BeautifulSoup(html.read(), 'lxml')
details = soup.find_all('font', {'face': 'verdana'})[10:]
result = []
for detail in details:
siteName = details[0].text
licNum = details[2].text
siteRank = details[4].text
expDate = details[6].text
primeStatus = details[8].text
secStatus = details[10].text
siteAddress = details[12].text
inspectResult = details[20].text
observed1 = details[34].get_text
observed2 = details[36].text
observed3 = details[38].text
observed4 = details[40].text
observed5 = details[42].text
observed6 = details[44].text
observed7 = details[46].text
observed8 = details[48].text
observed9 = details[50].text
observed10 = details[52].text
detailsLib = {
'Restaurant': siteName,
'License': licNum,
'Rank': siteRank,
'Expires': expDate,
'Primary': primeStatus,
'Secondary': secStatus,
'Address': siteAddress,
'Result': inspectResult,
'Observed1': observed1,
'Observed2': observed2,
'Observed3': observed3,
'Observed4': observed4,
'Observed5': observed5,
'Observed6': observed6,
'Observed7': observed7,
'Observed8': observed8,
'Observed9': observed9,
'Observed10': observed10
}
result.append(detailsLib)
return result
for url in urls:
repr(get_inspect_detail(url))

removing certain characters from entries within a list

I need to remove the [',\n\xa0 characters and the years (1994) from this entry in the list then iterate over the list doing this to each entry.
is there a way I can do this? I'm newish to python and have been trying for hours
The entries are like so :
[['The Shawshank Redemption\n(1994)\n\n\n 9.2\xa0\xa0\n\n'], ['The Godfather\n(1972)\n\n\n 9.2\xa0\xa0\n\n'], ['The Godfather: Part II\n(1974)\n\n\n 9.0\xa0\xa0\n\n'],
edit: sorry for not including the code, iv managed to strip the numbers and the \n newline characters after the year. but still getting newlines character just after the film title. ill paste my code anwyway thanks!:
from bs4 import BeautifulSoup
import requests
import random
names = []
newList = []
url = 'http://m.imdb.com/chart/top'
# get contents from url
content = requests.get(url).content
# get soup
soup = BeautifulSoup(content,'lxml') # choose lxml parser
# find all the references
ref_tags = soup.findAll('span', { 'class' : 'media-body' })
realTags = soup.find_all("h4")
# iterate through the ResultSet
for i,ref_tag in enumerate(ref_tags):
# print text only
names.append('[{0}] {1}'.format(i,ref_tag.text))
pos = 0
for name in names:
newName = names[pos]
newName = newName[9:]
newName = newName[:100]
newName = newName.split("(")
newName = newName[::2]
del newName[2:9:3]
newList.append(newName)
pos = pos + 1
print(newList)
choice = random.choice(newList)
print(choice)
the output is like this:
[['The Shawshank Redemption\n'], ['The Godfather\n'], ['The Godfather: Part II\n'], ['The Dark Knight\n'], ['12 Angry Men\n']
so i got it to output how i would like. thanks any!
heres the code for anyone who may need it in future:
from bs4 import BeautifulSoup
import requests
import random
names = []
newList = []
url = 'http://m.imdb.com/chart/top'
# get contents from url
content = requests.get(url).content
# get soup
soup = BeautifulSoup(content,'lxml') # choose lxml parser
# find all the references
ref_tags = soup.findAll('span', { 'class' : 'media-body' })
realTags = soup.find_all("h4")
# iterate through the ResultSet
for i,ref_tag in enumerate(ref_tags):
# print text only
names.append('[{0}] {1}'.format(i,ref_tag.text))
pos = 0
for name in names:
newName = names[pos]
newName = newName[9:]
newName = newName[:100]
newName = newName.split("(")
newName = newName[::2]
del newName[2:9:3]
newList.append(newName)
pos = pos + 1
wordChoice = random.choice(newList)
str = str(wordChoice)
editWord = str.split("\\n")
print(editWord[1])
and the output is like so:
Shutter Island

Resources