I have the following IPython Notebook, I am trying to access data base of movies from rotten tomatoes website.
But Rotten Tomatoes limits to 10,000 API requests a day
So I don't want to re-run this function every time when I restart the notebook, I am trying to save and reload this data as a CSV file. When I convert the data to a csv file I am getting this processing symbol[*] inside IPython notebook. After some time I am getting the following error
ConnectionError: HTTPConnectionPool(host='api.rottentomatoes.com', port=80): Max retries exceeded with url: /api/public/v1.0/movie_alias.json?apikey=5xr26r2qtgf9h3kcq5kt6y4v&type=imdb&id=0113845 (Caused by <class 'socket.gaierror'>: [Errno 11002] getaddrinfo failed)
Is this problem due to slow internet connection? Should I make some changes to my code? Kindly help me with this.
The code for the file is shown below:
%matplotlib inline
import json
import requests
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
api_key = '5xr26r2qtgf9h3kcq5kt6y4v'
movie_id = '770672122' # toy story 3
url = 'http://api.rottentomatoes.com/api/public/v1.0/movies/%s/reviews.json' % movie_id
#these are "get parameters"
options = {'review_type': 'top_critic', 'page_limit': 20, 'page': 1, 'apikey': api_key}
data = requests.get(url, params=options).text
data = json.loads(data) # load a json string into a collection of lists and dicts
print json.dumps(data['reviews'][0], indent=2) # dump an object into a json string
from io import StringIO
movie_txt = requests.get('https://raw.github.com/cs109/cs109_data/master/movies.dat').text
movie_file = StringIO(movie_txt) # treat a string like a file
movies = pd.read_csv(movie_file,delimiter='\t')
movies
#print the first row
movies[['id', 'title', 'imdbID', 'year']]
def base_url():
return 'http://api.rottentomatoes.com/api/public/v1.0/'
def rt_id_by_imdb(imdb):
"""
Queries the RT movie_alias API. Returns the RT id associated with an IMDB ID,
or raises a KeyError if no match was found
"""
url = base_url() + 'movie_alias.json'
imdb = "%7.7i" % imdb
params = dict(id=imdb, type='imdb', apikey=api_key)
r = requests.get(url, params=params).text
r = json.loads(r)
return r['id']
def _imdb_review(imdb):
"""
Query the RT reviews API, to return the first page of reviews
for a movie specified by its IMDB ID
Returns a list of dicts
"""
rtid = rt_id_by_imdb(imdb)
url = base_url() + 'movies/{0}/reviews.json'.format(rtid)
params = dict(review_type='top_critic',
page_limit=20,
page=1,
country='us',
apikey=api_key)
data = json.loads(requests.get(url, params=params).text)
data = data['reviews']
data = [dict(fresh=r['freshness'],
quote=r['quote'],
critic=r['critic'],
publication=r['publication'],
review_date=r['date'],
imdb=imdb, rtid=rtid
) for r in data]
return data
def fetch_reviews(movies, row):
m = movies.irow(row)
try:
result = pd.DataFrame(_imdb_review(m['imdbID']))
result['title'] = m['title']
except KeyError:
return None
return result
def build_table(movies, rows):
dfs = [fetch_reviews(movies, r) for r in range(rows)]
dfs = [d for d in dfs if d is not None]
return pd.concat(dfs, ignore_index=True)
critics = build_table(movies, 3000)
critics.to_csv('critics.csv', index=False)
critics = pd.read_csv('critics.csv')
Related
Im trying to scrape a website for multiple values regarding a list of books. The links to the book pages are stored in a dataframe. Now I need a function that iterates those links and adds the book values to new columns in the dataframe. I don't want to request the page again every time I'm scraping a new book value, so I want to do it all in one function.
The problem is the function then returns multiple values (e.g. book_title and book_rating) which I don't know how to best add to the dataframe.
I tried the following, which I know can't work but I'm stuck:
import requests as rq
from bs4 import BeautifulSoup as bs
import pandas as pd
#function to get the book page
def get_book_page(page):
# Construct the URL
books_page_url = page
# Get the HTML page content using requests
response = rq.get(books_page_url, headers = headers)
# Ensure that the response is valid
if response.status_code != 200:
print('Status code:', response.status_code)
raise Exception('Failed to fetch web page ' + books_page_url)
# Construct a beautiful soup document
doc = bs(response.content, "html.parser")
return doc
#function to scrape the book title
def scrape_book_title(book_content):
try:
title_tag = book_content.find("h1", class_="bc-heading bc-color-base bc-size-large bc-text-bold").text.strip()
except:
title_tag = "fehlt"
return title_tag
#function to scrape the book rating
def scrape_book_rating(book_content):
star_tag = book_content.find("li", class_="bc-list-item ratingsLabel")
try:
rating_tag = star_tag.find("span", class_="bc-text bc-pub-offscreen").text.strip()
except:
rating_tag = "fehlt"
return rating_tag
#function I'm trying to fix
def get_book_title(links):
bs_page = get_book_page(links)
bs_content = bs_page.find("ul", class_="bc-list bc-spacing-s2 bc-color-secondary bc-list-nostyle")
book_title = scrape_book_title(bs_content)
book_rating = scrape_book_rating(bs_content)
return book_title, book_rating
#here I would like to add the columns "A_Titel" and "A_Rating" with the values of "book_title" and "book_rating"
df['A_Titel'], df['A_Rating'] = df.apply(lambda x: get_book_title(x.Link), axis=1)
I'm running this flask app
from flask import Flask, request, jsonify, render_template
from flask_cors import CORS, cross_origin
import json
import pandas as pd
# Create the app object
app = Flask(__name__)
cors = CORS(app, resources= {r"/*": {'origins' : "*"}})
# importing function for calculations
from Record_Matching import Matching
#app.route("/query", methods = ['get'])
#cross_origin()
def query():
# service_account_creds = request.json
query1 = request.args.get('query1', type = str)
query2 = request.args.get('query2', type = str)
querycolumns = request.args.get('querycolumns')
project_id = request.args.get('project_id', type = str)
service_account_creds = request.args.get('service_account')
SS = request.args.get('SS', type = float)
TT = request.args.get('TT', type = float)
result = Matching(query1,query2, SS,TT, service_account_creds, project_id, querycolumns)
return result
if __name__ == "__main__":
app.run(host="localhost", port=8080, debug=True)
and I'm importing the matching function from this python scripts
import pandas as pd
from google.cloud import bigquery
from google.oauth2 import service_account
import recordlinkage
from recordlinkage.preprocessing import phonetic
from pandas.io.json import json_normalize
import uuid
from uuid import uuid4
import random
import string
import json
import ast
# Results to data frame function
def gcp2df(sql, client):
query = client.query(sql)
results = query.result()
return results.to_dataframe()
# Exporting df to bigquery - table parameter example: "dataset.tablename"
# def insert(df, table):
# client = bigquery.Client()
# job_config = bigquery.LoadJobConfig(write_disposition=bigquery.job.WriteDisposition.WRITE_TRUNCATE)
# return client.load_table_from_dataframe(df, table, job_config = job_config)
def pair(df1, df2, TT, querycolumns):
# function to take pair from list and compare:
L = querycolumns
l=len(querycolumns)
p1=0
p2=1
# To generate phonetics we need to make sure all names are in english.
# thus we'll replace non-english words by random english strings
df1[L[p1]] = df1[L[p1]].astype(str)
df2[L[p2]] = df2[L[p2]].astype(str)
for i in range(0,len(df1)):
if df1[L[p1]][i].isascii() == False:
df1[L[p1]][i] = ''.join(random.choices(string.ascii_lowercase, k=5))
for i in range(0,len(df2)):
if df2[L[p2]][i].isascii() == False:
df2[L[p2]][i] = ''.join(random.choices(string.ascii_lowercase, k=5))
compare = recordlinkage.Compare()
df1["phonetic_given_name"] = phonetic(df1[L[p1]], "soundex")
df2["phonetic_given_name"] = phonetic(df2[L[p2]], "soundex")
df1["initials"] = (df1[L[p1]].str[0] + df1[L[p1]].str[-1])
df2["initials"] = (df2[L[p2]].str[0] + df2[L[p2]].str[-1])
indexer = recordlinkage.Index()
indexer.block('initials')
candidate_links = indexer.index(df1, df2)
compare.exact('phonetic_given_name', 'phonetic_given_name', label="phonetic_given_name")
# O(n) a function that uses two pointers to track consecutive pairs for the input list
while p2 <=l:
compare.string(L[p1], L[p2], method='jarowinkler',threshold = TT, label=L[p1])
p1+=2
p2+=2
features = compare.compute(candidate_links,df1, df2)
return features
def Matching(query1,query2, SS,TT, service_account_creds, project_id, querycolumns):
service_account_creds = ast.literal_eval(service_account_creds)
credentials = service_account.Credentials(service_account_creds, service_account_creds['client_email'],
service_account_creds['token_uri'])
job_config = bigquery.LoadJobConfig()
client = bigquery.Client( project = project_id)
SS=int(SS)
TT=float(TT)
df1 = gcp2df("""{}""".format(query1), client)
df2 = gcp2df("""{}""".format(query2), client)
querycolumns = json.loads(querycolumns)
querycolumns = list(querycolumns.values())
features = pair(df1, df2, TT, querycolumns)
features['Similarity_score'] = features.sum(axis=1)
features = features[features['Similarity_score']>=SS].reset_index()
final = features[['level_0', 'level_1']]
final.rename(columns= {'level_0':'df1_index', 'level_1':'df2_index'}, inplace= True)
final['Unique_ID'] = [uuid.uuid4() for _ in range(len(final.index))]
final['Unique_ID'] = final['Unique_ID'].astype(str)
final['Similarity_Score'] = SS
final_duplicates = final['df1_index'].value_counts().max()
# insert(final,"test-ahmed-project.Record_Linkage.Matching_Indices")
message = "Mission accomplished!, your highest number of duplicates is " + str(final_duplicates)
return {'message':message,'final':final.to_dict('records'), 'df1':df1.to_dict('records')}
I'm not sure why when I return df1 as a dictionary it shows ValueError error when I try to to use the function from flask app, but when I run it in a jupytor notebook using the same dataframe that I'm taking from bigquery, it works just fine, so why does it not work on the flask app?
I tried to_dict('record') to convert a dataframe to a dictionary,
it looking online many resources suggest the error exists because the data contains missing values, but it shouldn't be a problem because when I try converting the same dataframe to dictionary in jupyter notebook it works just fine.
The below functions extract content from 'http://thegreyhoundrecorder.com.au/form-guides/' and append all content to a list. The function works fine, although the speed at which the content is scraped from the website is slow. This line tree = html.fromstring(page.content) in particular slows down the process. Is there a way I can improve on the speed of my request.
import lxml
from lxml import html
import requests
import re
import pandas as pd
from requests.exceptions import ConnectionError
greyhound_url = 'http://thegreyhoundrecorder.com.au/form-guides/'
def get_page(url):
"""fxn take page url and return the links to the acticle(Field) we
want to scrape in a list.
"""
page = requests.get(url)
tree = html.fromstring(page.content)
my_list = tree.xpath('//tbody/tr/td[2]/a/#href') # grab all link
print('Length of all links = ', len(my_list))
my_url = [page.url.split('/form-guides')[0] + str(s) for s in my_list]
return my_url
def extract_data(my_url):
"""
fxn take a list of urls and extract the needed infomation from
greyhound website.
return: a list with the extracted field
"""
new_list = []
try:
for t in my_url:
print(t)
page_detail = requests.get(t)
tree_1 = html.fromstring(page_detail.content)
title = ''.join(tree_1.xpath('//div/h1[#class="title"]/text()'))
race_number = tree_1.xpath("//tr[#id = 'tableHeader']/td[1]/text()")
Distance = tree_1.xpath("//tr[#id = 'tableHeader']/td[3]/text()")
TGR_Grade = tree_1.xpath("//tr[#id = 'tableHeader']/td[4]/text()")
TGR1 = tree_1.xpath("//tbody/tr[#class='fieldsTableRow raceTipsRow']//div/span[1]/text()")
TGR2 = tree_1.xpath("//tbody/tr[#class='fieldsTableRow raceTipsRow']//div/span[2]/text()")
TGR3 = tree_1.xpath("//tbody/tr[#class='fieldsTableRow raceTipsRow']//div/span[3]/text()")
TGR4 = tree_1.xpath("//tbody/tr[#class='fieldsTableRow raceTipsRow']//div/span[4]/text()")
clean_title = title.split(' ')[0].strip()
#clean title and extract track number
Track = title.split(' ')[0].strip()
#clean title and extract track date
date = title.split('-')[1].strip()
#clean title and extract track year
year = pd.to_datetime('now').year
#convert date to pandas datetime
race_date = pd.to_datetime(date + ' ' + str(year)).strftime('%d/%m/%Y')
#extract race number
new_rn = []
for number in race_number:
match = re.search(r'^(.).*?(\d+)$', number)
new_rn.append(match.group(1) + match.group(2))
new_list.append((race_date,Track,new_rn,Distance,TGR_Grade,TGR1,TGR2,TGR3,TGR4))
return new_list
except ConnectionError as e:
print('Connection error, connect to a stronger network or reload the page')
I am reading from a bigquery table to generate a payload to upload to FB conversions api.
cols=["payload","client_user_agent","event_source_url"]
I am copying the column values directly from the bq table as I am unable to print the full output of the dataframe in note book.
payload="{"pageDetail":{"pageName":"Confirmation","pageContentType":"cart","pageSiteSection":"cart","breadcrumbs":[{"title":"Home","url":"/en/home.html"},{"title":"Cart","url":"/cart"},{"title":"Confirmation","url":"/order-confirmation="}],"pageCategory":"Home","pageCategory1":"Cart","pageCategory2":"Confirmation","proBtbGlobalHeader":false},"orderDetails":{"hceid":"3b94a","orderConfirmed":true,"orderDate":"2021-01-15","orderId":"0123","unique":2,"pricingSummary":{"total":54.01},"items":[{"productId":"0456","quantity":1,"shippingAddress":{"postalCode":"V4N 3X3"},"promotion":{"voucherCode":null},"clickToInstall":{"eligible":false}},{"productId":"0789","quantity":1,"fulfillment":{"fulfillmentCost":""},"shippingAddress":{"postalCode":"A4N 3Y3"},"promotion":{"voucherCode":null},"clickToInstall":{"eligible":false}}],"billingAddress":{"postalCode":"M$X1A7"}},"event":{"type":"Load","page":"Confirmation","timestamp":1610706772998,"language":"English","url":"https://www"}}"
client_user_agent="Mozilla/5.0"
event_source_url= "https://www.def.com="
I need the value for email=[orderDetails][hceid] and value=["orderDetails"]["pricingSummary"]["total"]
Initially all the payload I wanted was in a single column and I was able to achieve the uploads with the following code
import time
from facebook_business.adobjects.serverside.event import Event
from facebook_business.adobjects.serverside.event_request import EventRequest
from facebook_business.adobjects.serverside.user_data import UserData
from facebook_business.adobjects.serverside.custom_data import CustomData
from facebook_business.api import FacebookAdsApi
import pandas as pd
import json
FacebookAdsApi.init(access_token=access_token)
query='''SELECT JSON_EXTRACT(payload, '$') AS payload FROM `project.dataset.events` WHERE eventType = 'Page Load' AND pagename = "Confirmation" limit 1'''
df = pd.read_gbq(query, project_id= project, dialect='standard')
payload = df.to_dict(orient="records")
for i in payload:
#print(type(i["payload"]))
k = json.loads(i["payload"])
email = k["orderDetails"]["hcemuid"]
user_data = UserData(email)
value=k["orderDetails"]["pricingSummary"]["total"]
order_id = k["orderDetails"]["orderId"]
custom_data = CustomData(
currency='CAD',
value=value)
event = Event(
event_name='Purchase',
event_time=int(time.time()),
user_data=user_data,
custom_data=custom_data,
event_id = order_id,
data_processing_options= [])
events = [event]
#print(events)
event_request = EventRequest(
events=events,
test_event_code='TEST8609',
pixel_id=pixel_id)
#print(event_request)
a=event_request.execute()
print(a)
Now there are additional values client_user_agent that needs to be part of user data and event_source_url as parts of events in the above code that are present as two different columns in GBQ table.
I have tried similar code as above for multiple columns but I am receiving a
TypeError: Object of type Series is not JSON serializable
So I tried concatenating the columns and then create a json serializable object but I am not able to do an upload.
Below is where I am stuck and lost and not sure how to proceed further any inputs appreciated.
import time
from facebook_business.adobjects.serverside.event import Event
from facebook_business.adobjects.serverside.event_request import EventRequest
from facebook_business.adobjects.serverside.user_data import UserData
from facebook_business.adobjects.serverside.custom_data import CustomData
from facebook_business.api import FacebookAdsApi
import pandas as pd
import json
FacebookAdsApi.init(access_token=access_token)
query='''SELECT payload AS payload,location.userAgent as client_user_agent,location.referrer as event_source_url FROM `project.Dataset.events` WHERE eventType = 'Page Load' AND pagename = "Confirmation" limit 1'''
df = pd.read_gbq(query, project_id= project, dialect='standard')
df.reset_index(drop=True, inplace=True)
payload = df.to_dict(orient="records")
print(payload)
## cols = ['payload', 'client_user_agent', 'event_source_url']
## df['combined'] = df[cols].apply(lambda row: ','.join(row.values.astype(str)), axis=1)
## del df["payload"]
## del df["client"]
## del df["source"]
## payload = df.to_dict(orient="records")
#tried concatinating all columns in a the dataframe but not able to create a valid json object for upload
columns = ['payload', 'client_user_agent', 'event_source_url']
df['payload'] = df['payload'].str.replace(r'}"$', '')
payload = df[columns].to_dict(orient='records')
print(payload)
## df = df.drop(columns=columns)
## pd.options.display.max_rows = 4000
# #print(payload)
# for i in payload:
# print(i["payload"])
# k = json.loads(i["payload"])
# email = k["orderDetails"]["hcemuid"]
# print(email)
I am following the instructions from this page:https://developers.facebook.com/docs/marketing-api/conversions-api
I have used the bigquery json_extract_scalar function to extract data from nested column instead of pandas which is a relatively better solution for my scenario.
I am trying to implement a time fold function to be 'map'ed to various partitions of a dask dataframe which in turn changes the shape of the dataframe in question (or alternatively produces a new dataframe with the altered shape). This is how far I have gotten. The result 'res' returned on compute is a list of 3 delayed objects. When I try to compute each of them in a loop (last tow lines of code) this results in a "TypeError: 'DataFrame' object is not callable" After going through the examples for map_partitions, I also tried altering the input DF (inplace) in the function with no return value which causes a similar TypeError with NoneType. What am I missing?
Also, looking at the visualization (attached) I feel like there is a need for reducing the individually computed (folded) partitions into a single DF. How do I do this?
#! /usr/bin/env python
# Start dask scheduler and workers
# dask-scheduler &
# dask-worker --nthreads 1 --nprocs 6 --memory-limit 3GB localhost:8786 --local-directory /dev/shm &
from dask.distributed import Client
from dask.delayed import delayed
import pandas as pd
import numpy as np
import dask.dataframe as dd
import math
foldbucketsecs=30
periodicitysecs=15
secsinday=24 * 60 * 60
chunksizesecs=60 # 1 minute
numts = 5
start = 1525132800 # 01/05
end = 1525132800 + (3 * 60) # 3 minute
c = Client('127.0.0.1:8786')
def fold(df, start, bucket):
return df
def reduce_folds(df):
return df
def load(epoch):
idx = []
for ts in range(0, chunksizesecs, periodicitysecs):
idx.append(epoch + ts)
d = np.random.rand(chunksizesecs/periodicitysecs, numts)
ts = []
for i in range(0, numts):
tsname = "ts_%s" % (i)
ts.append(tsname)
gts.append(tsname)
res = pd.DataFrame(index=idx, data=d, columns=ts, dtype=np.float64)
res.index = pd.to_datetime(arg=res.index, unit='s')
return res
gts = []
load(start)
cols = len(gts)
idx1 = pd.DatetimeIndex(start=start, freq=('%sS' % periodicitysecs), end=start+periodicitysecs, dtype='datetime64[s]')
meta = pd.DataFrame(index=idx1[:0], data=[], columns=gts, dtype=np.float64)
dfs = [delayed(load)(fn) for fn in range(start, end, chunksizesecs)]
from_delayed = dd.from_delayed(dfs, meta, 'sorted')
nfolds = int(math.ceil((end - start)/foldbucketsecs))
cprime = nfolds * cols
gtsnew = []
for i in range(0, cprime):
gtsnew.append("ts_%s,fold=%s" % (i%cols, i/cols))
idx2 = pd.DatetimeIndex(start=start, freq=('%sS' % periodicitysecs), end=start+foldbucketsecs, dtype='datetime64[s]')
meta = pd.DataFrame(index=idx2[:0], data=[], columns=gtsnew, dtype=np.float64)
folded_df = from_delayed.map_partitions(delayed(fold)(from_delayed, start, foldbucketsecs), meta=meta)
result = c.submit(reduce_folds, folded_df)
c.gather(result).visualize(filename='/usr/share/nginx/html/svg/df4.svg')
res = c.gather(result).compute()
for f in res:
f.compute()
Never mind! It was my fault, instead of wrapping my function in delayed I simply passed it to the map_partitions call like so and it worked.
folded_df = from_delayed.map_partitions(fold, start, foldbucketsecs, nfolds, meta=meta)