I am trying to export Data from json format in CSV but getting no results.
below is the code
import requests
from bs4 import BeautifulSoup
import json
import re
url = "https://www.daraz.pk/catalog/?q=dell&_keyori=ss&from=input&spm=a2a0e.home.search.go.35e34937qjElRf"
page = requests.get(url)
print(page.status_code)
print(page.text)
soup = BeautifulSoup(page.text, 'html.parser')
print(soup.prettify())
alpha = soup.find_all('script',{'type':'application/ld+json'})
jsonObj =`json.loads(alpha[1].text)`
for item in jsonObj['itemListElement']:
name = item['name']
price = item['offers']['price']
currency = item['offers']['priceCurrency']
availability = item['offers']['availability'].split('/')[-1]
availability = [s for s in re.split("([A-Z][^A-Z]*)", availability) if s]
availability = ' '.join(availability)
print('Availability: %s Price: %0.2f %s Name: %s' %(availability,float(price), currency,name))
Here is the code I am trying to export Data in CSV but not getting results in CSV
Create a file to write to, add headers row
outfile = open('products.csv','w', newline='')
writer = csv.writer(outfile)
writer.writerow(["name", "offers", "price", "priceCurrency", "availability" ])
outfile.close()
alpha = soup.find_all('script',{'type':'application/ld+json'})
jsonObj = json.loads(alpha[1].text)
for item in jsonObj['itemListElement']:
name = item['name']
price = item['offers']['price']
currency = item['offers']['priceCurrency']
availability = item['offers']['availability'].split('/')[-1]
availability = [s for s in re.split("([A-Z][^A-Z]*)", availability) if s]
availability = ' '.join(availability)
you get not result because not writing the CSV in the loop
outfile = open('products.csv','w', newline='')
writer = csv.writer(outfile)
writer.writerow(["name", "type", "price", "priceCurrency", "availability" ])
alpha = soup.find_all('script',{'type':'application/ld+json'})
jsonObj = json.loads(alpha[1].text)
for item in jsonObj['itemListElement']:
name = item['name']
type = item['#type']
price = item['offers']['price']
currency = item['offers']['priceCurrency']
availability = item['offers']['availability'].split('/')[-1]
# forgot this?
writer.writerow([name, type, price, currency, availability ])
# and close the CSV here
outfile.close()
I personally am a fan of Pandas to write a csv. Some might say its extensive. But it works.
import requests
from bs4 import BeautifulSoup
import json
import re
import pandas as pd
url = "https://www.daraz.pk/catalog/?q=dell&_keyori=ss&from=input&spm=a2a0e.home.search.go.35e34937qjElRf"
page = requests.get(url)
#print(page.status_code)
#print(page.text)
soup = BeautifulSoup(page.text, 'html.parser')
#(soup.prettify())
alpha = soup.find_all('script',{'type':'application/ld+json'})
jsonObj = json.loads(alpha[1].text)
results = pd.DataFrame()
for item in jsonObj['itemListElement']:
name = item['name']
price = item['offers']['price']
currency = item['offers']['priceCurrency']
availability = item['offers']['availability'].split('/')[-1]
availability = [s for s in re.split("([A-Z][^A-Z]*)", availability) if s]
availability = ' '.join(availability)
row = [name,price,currency,availability]
temp_df = pd.DataFrame([row], columns = ['name','price','currency','availability'])
results = results.append(temp_df)
results.to_csv('products.csv', index=False)
Related
The code below gives me the following error:
ValueError: Length mismatch: Expected axis has 0 elements, new values have 1 elements
on the df.columns = ["GP Practice Name"] line.
I tried
import pandas as pd
import requests
from bs4 import BeautifulSoup
postal_codes = ["2000", "2010", "2020", "2030", "2040"]
places_by_postal_code = {}
def get_places(postal_code):
url = f"https://www.yellowpages.com.au/search/listings?clue={postal_code}&locationClue=&latitude=&longitude=&selectedViewMode=list&refinements=category:General%20Practitioner&selectedSortType=distance"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
places = soup.find_all("div", {"class": "listing-content"})
return [place.find("h2").text for place in places]
for postal_code in postal_codes:
places = get_places(postal_code)
places_by_postal_code[postal_code] = places
df = pd.DataFrame.from_dict(places_by_postal_code, orient='index')
df.columns = ["GP Practice Name"]
df = pd.DataFrame(places_by_postal_code.values(), index=places_by_postal_code.keys(), columns=["GP Practice Name"])
print(df)
and was expecting a list of GPs for the postcodes specified in the postal_codes variable.
How can I use a list of words and make the program pull out any new headings containing any one of the words inside the list. It gives out a error if I try to use the list of key words.
import requests
from bs4 import BeautifulSoup
import csv
from datetime import datetime, timedelta
s_date = '2018/01/01'
e_date = '2018/01/06'
d1 = datetime.strptime(s_date, '%Y/%m/%d')
d2 = datetime.strptime(e_date, '%Y/%m/%d')
delta = timedelta(days = 1)
date_list = list()
while d1 <= d2:
# print(d1.strftime('%Y/%m/%d'))
date_list.append(d1.strftime('%Y/%m/%d'))
d1 += delta
print(date_list)
for d in date_list:
URL = 'https://www.thedailystar.net/newspaper?date={}'.format(d)
result = requests.get(URL)
src = result.text
soup = BeautifulSoup(src, 'lxml')
# filename = 'new.csv'
# f = open(filename, 'w', newline = '')
# fx = csv.writer(f)
containers = soup.find_all('div',class_ = 'list-content')
key_words = ['Road', 'crash', 'dead', 'accidents']
key_word = input('Enter the desired word to search the news: ')
for c in containers:
headings = c.h5.a.text
if key_word in headings:
print(headings)
with open('nw.txt', 'w') as f:
f.write(headings)
# fx.writerow(headings)
You had several bugs in your code, that's why it didn't work as expected.
Here's the correct version of what you want to achieve:
import requests
from bs4 import BeautifulSoup
import csv
from datetime import datetime, timedelta
s_date = '2018/01/01'
e_date = '2018/01/06'
d1 = datetime.strptime(s_date, '%Y/%m/%d')
d2 = datetime.strptime(e_date, '%Y/%m/%d')
delta = timedelta(days = 1)
date_list = list()
while d1 <= d2:
date_list.append(d1.strftime('%Y/%m/%d'))
d1 += delta
print(date_list)
with open('nw.txt', 'w') as f:
for d in date_list:
URL = 'https://www.thedailystar.net/newspaper?date={}'.format(d)
result = requests.get(URL)
src = result.text
soup = BeautifulSoup(src, 'lxml')
containers = soup.find_all('div',class_ = 'list-content')
key_words = ['Road', 'crash', 'dead', 'accidents']
# key_word = input('Enter the desired word to search the news: ')
for c in containers:
headings = c.h5.a.text
if any(key_word in headings for key_word in key_words):
print(headings)
f.write(headings + '\n')
What's happening (changes are at the bottom):
If you wanted to use a list of keywords (which is called key_words), then an option is to use built-in any function and iterate over all of keywords, checking wherther it is in your current headings.
Also you're open-ing file every time you want to write - it destroys last write and creates a new file. Instead you should open file once before loop.
Plus when you were writing headings to file, you didn't add \n which is the newline symbol - it would cause all headings to append as one row.
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)
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')
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))