Server side previous page call not working - python-3.x

I configured the server-side processing of datatables. On the server side I use python3 and mongodb.
I think my paging logic is good as you can see from the code:
PYTHON:
#bp.route('/_ajax_products', methods=['GET', 'POST'])
#login_required
def ajax_products():
num = int(request.args.get('page_num')) + 1
total_items = product_db.count()
items_to_show = 100
result = {"draw": num, "recordsTotal": total_items, "recordsFiltered": total_items}
list_prod = product_db.find().sort([("Code", 1)]).skip(items_to_show * (num - 1)).limit(items_to_show)
final_list = []
for i in list_prod:
# iteration on products and addition to the final list
result['data'] = final_list
return jsonify(result)
DATATABLE INITIALISATION:
$('#ProductsList').DataTable({
"dom": 'Brlf<t><"clear">p',
"pageLength": 100,
select: true,
"processing": true,
"serverSide": true,
"ajax": {
url:"/_ajax_products",
data: function ( d ) {
var datatable = $('#ProductsList').DataTable();
var currentPage = datatable.page.info().page;
d.page_num = currentPage;
}
},
"columns":[...]
...
})
The data loads well in my datatable. When I call the next page either there is no problem.
The problem appears when I call a previous page.
The display starts on page 1. when I press for example the pagination button 3, I can see in my console:
"GET /_ajax_products?draw=3&
But when I try to go back to page 1, the draw parameter goes to 4:
"GET /_ajax_products?draw=4&
... and it continues to increment.
On the server side the good data are found but they are not displayed in the datatable.
How can I solve this problem?

I finally found a solution. The error came from a misunderstanding of what the draw option was doing.
Indeed I thought that the value of draw corresponded to the page to be displayed, which is not the case.
Here is the new version of the code in case it can help someone:
#bp.route('/_ajax_products', methods=['GET', 'POST'])
#login_required
def ajax_products():
num = int(request.args.get('page_num')) + 1
total_items = product_db.count()
items_to_show = 100
result = {"recordsTotal": total_items, "recordsFiltered": total_items}
list_prod = product_db.find().sort([("Code", 1)]).skip(items_to_show * (num - 1)).limit(items_to_show)
final_list = []
for i in list_prod:
# iteration on products and addition to the final list
result['data'] = final_list
return jsonify(result)

Related

How to ignore videos with like count disabled while using YouTube Data API V3

In a YouTube search result, some videos have their likes hidden. My code fails when it reaches those videos:
KeyError : 'likeCount'.
Is there a way to ignore such videos and continue with my iteration?
request = youtube.videos().list(part = "snippet,statistics", id = LIST)
A = request.execute()
for j in range(len(A['items'])):
Data.append({
'Views': A['items'][j]['statistics']['viewCount'],
'Likes': A['items'][j]['statistics']['likeCount'],
'Dislikes': A['items'][i]['statistics']['dislikeCount']
})
I would rewrite your original code as below:
request = youtube.videos().list(
part = "snippet,statistics",
id = LIST
)
response = request.execute()
for item in response.get('items', []):
stat = item['statistics']
# items without 'like' and 'dislike'
# count get those counts to be 0
Data.append({
'Views': stat.get('viewCount', 0),
'Likes': stat.get('likeCount', 0),
'Dislikes': stat.get('dislikeCount', 0)
})
Notice that all statistics data under the statistics property of the response obtained from the API is accessed with the get method, such that, if the respective property does not exists, then its associated value is taken to be 0.
Another possibility for your for loop above would look as follows:
for item in response.get('items', []):
stat = item['statistics']
# items without 'like' and 'dislike'
# counts are being ignored
if stat.get('likeCount') is None or \
stat.get('dislikeCount') is None:
continue
Data.append({
'Views': stat['viewCount'],
'Likes': stat['likeCount'],
'Dislikes': stat['dislikeCount']
})

Python list add variables in rows

im trying to add variables to a list that i created. Got a result from a session.execute.
i´ve done this:
def machine_id(session, machine_serial):
stmt_raw = '''
SELECT
id
FROM
machine
WHERE
machine.serial = :machine_serial_arg
'''
utc_now = datetime.datetime.utcnow()
utc_now_iso = pytz.utc.localize(utc_now).isoformat()
utc_start = datetime.datetime.utcnow() - datetime.timedelta(days = 30)
utc_start_iso = pytz.utc.localize(utc_start).isoformat()
stmt_args = {
'machine_serial_arg': machine_serial,
}
stmt = text(stmt_raw).columns(
#ts_insert = ISODateTime
)
result = session.execute(stmt, stmt_args)
ts = utc_now_iso
ts_start = utc_start_iso
ID = []
for row in result:
ID.append({
'id': row[0],
'ts': ts,
'ts_start': ts_start,
})
return ID
In trying to get the result over api like this:
def form_response(response, session):
result_machine_id = machine_id(session, machine_serial)
if not result_machine_id:
response['Error'] = 'Seriennummer nicht vorhanden/gefunden'
return
response['id_timerange'] = result_machine_id
Output looks fine.
{
"id_timerange": [
{
"id": 1,
"ts": "2020-08-13T08:32:25.835055+00:00",
"ts_start": "2020-07-14T08:32:25.835089+00:00"
}
]
}
Now i only want the id from it as a parameter for another function. Problem is i think its not a list. I cant select the first element. result_machine_id[0] result is like the posted Output. I think in my first function i only add ts & ts_start to the first row? Is it possible to add emtpy rows and then add 'ts':ts as value?
Help would be nice
If I have understood your question correctly ...
Your output looks like dict. so access its id_timerange key which gives you a list. Access the first element which gives you another dict. On this dict you have an id key:
result_machine_id["id_timerange"][0]["id"]

Pygal bar chart says “No data”

I am trying to create a bar graph in pygal that uses the api for hacker news and charts the most active news based on comments. I posted my code below, but I cannot figure out why my graph keep saying "No data"??? Any suggestions? Thanks!
import requests
import pygal
from pygal.style import LightColorizedStyle as LCS, LightenStyle as LS
from operator import itemgetter
# Make an API call, and store the response.
url = 'https://hacker-news.firebaseio.com/v0/topstories.json'
r = requests.get(url)
print("Status code:", r.status_code)
# Process information about each submission.
submission_ids = r.json()
submission_dicts = []
for submission_id in submission_ids[:30]:
# Make a separate API call for each submission.
url = ('https://hacker-news.firebaseio.com/v0/item/' +
str(submission_id) + '.json')
submission_r = requests.get(url)
print(submission_r.status_code)
response_dict = submission_r.json()
submission_dict = {
'comments': int(response_dict.get('descendants', 0)),
'title': response_dict['title'],
'link': 'http://news.ycombinator.com/item?id=' + str(submission_id),
}
submission_dicts.append(submission_dict)
# Visualization
my_style = LS('#336699', base_style=LCS)
my_config = pygal.Config()
my_config.show_legend = False
my_config.title_font_size = 24
my_config.label_font_size = 14
my_config.major_label_font_size = 18
my_config.show_y_guides = False
my_config.width = 1000
chart = pygal.Bar(my_config, style=my_style)
chart.title = 'Most Active News on Hacker News'
chart.add('', submission_dicts)
chart.render_to_file('hn_submissons_repos.svg')
The values in the array passed to the add function need to be either numbers or dicts that contain the key value (or a mixture of the two). The simplest solution would be to change the keys used when creating submission_dict:
submission_dict = {
'value': int(response_dict.get('descendants', 0)),
'label': response_dict['title'],
'xlink': 'http://news.ycombinator.com/item?id=' + str(submission_id),
}
Notice that link has become xlink, this is one of the optional parameters that are defined in the Value Configuration section of the pygal docs.

Assign Class attributes from list elements

I'm not sure if the title accurately describes what I'm trying to do. I have a Python3.x script that I wrote that will issue flood warning to my facebook page when the river near my home has reached it's lowest flood stage. Right now the script works, however it only reports data from one measuring station. I would like to be able to process the data from all of the stations in my county (total of 5), so I was thinking that maybe a class method may do the trick but I'm not sure how to implement it. I've been teaching myself Python since January and feel pretty comfortable with the language for the most part, and while I have a good idea of how to build a class object I'm not sure how my flow chart should look. Here is the code now:
#!/usr/bin/env python3
'''
Facebook Flood Warning Alert System - this script will post a notification to
to Facebook whenever the Sabine River # Hawkins reaches flood stage (22.3')
'''
import requests
import facebook
from lxml import html
graph = facebook.GraphAPI(access_token='My_Access_Token')
river_url = 'http://water.weather.gov/ahps2/river.php?wfo=SHV&wfoid=18715&riverid=203413&pt%5B%5D=147710&allpoints=143204%2C147710%2C141425%2C144668%2C141750%2C141658%2C141942%2C143491%2C144810%2C143165%2C145368&data%5B%5D=obs'
ref_url = 'http://water.weather.gov/ahps2/river.php?wfo=SHV&wfoid=18715&riverid=203413&pt%5B%5D=147710&allpoints=143204%2C147710%2C141425%2C144668%2C141750%2C141658%2C141942%2C143491%2C144810%2C143165%2C145368&data%5B%5D=all'
def checkflood():
r = requests.get(river_url)
tree = html.fromstring(r.content)
stage = ''.join(tree.xpath('//div[#class="stage_stage_flow"]//text()'))
warn = ''.join(tree.xpath('//div[#class="current_warns_statmnts_ads"]/text()'))
stage_l = stage.split()
level = float(stage_l[2])
#check if we're at flood level
if level < 22.5:
pass
elif level == 37:
major_diff = level - 23.0
major_r = ('The Sabine River near Hawkins, Tx has reached [Major Flood Stage]: #', stage_l[2], 'Ft. ', str(round(major_diff, 2)), ' Ft. \n Please click the link for more information.\n\n Current Warnings and Alerts:\n ', warn)
major_p = ''.join(major_r)
graph.put_object(parent_object='me', connection_name='feed', message = major_p, link = ref_url)
<--snip-->
checkflood()
Each station has different 5 different catagories for flood stage: Action, Flood, Moderate, Major, each different depths per station. So for Sabine river in Hawkins it will be Action - 22', Flood - 24', Moderate - 28', Major - 32'. For the other statinos those depths are different. So I know that I'll have to start out with something like:
class River:
def __init__(self, id, stage):
self.id = id #station ID
self.stage = stage #river level'
#staticmethod
def check_flood(stage):
if stage < 22.5:
pass
elif stage.....
but from there I'm not sure what to do. Where should it be added in(to?) the code, should I write a class to handle the Facebook postings as well, is this even something that needs a class method to handle, is there any way to clean this up for efficiency? I'm not looking for anyone to write this up for me, but some tips and pointers would sure be helpful. Thanks everyone!
EDIT Here is what I figured out and is working:
class River:
name = ""
stage = ""
action = ""
flood = ""
mod = ""
major = ""
warn = ""
def checkflood(self):
if float(self.stage) < float(self.action):
pass
elif float(self.stage) >= float(self.major):
<--snip-->
mineola = River()
mineola.name = stations[0]
mineola.stage = stages[0]
mineola.action = "13.5"
mineola.flood = "14.0"
mineola.mod = "18.0"
mineola.major = "21.0"
mineola.alert = warn[0]
hawkins = River()
hawkins.name = stations[1]
hawkins.stage = stages[1]
hawkins.action = "22.5"
hawkins.flood = "23.0"
hawkins.mod = "32.0"
hawkins.major = "37.0"
hawkins.alert = warn[1]
<--snip-->
So from here I'm tring to stick all the individual river blocks into one block. What I have tried so far is this:
class River:
... name = ""
... stage = ""
... def testcheck(self):
... return self.name, self.stage
...
>>> for n in range(num_river):
... stations[n] = River()
... stations[n].name = stations[n]
... stations[n].stage = stages[n]
...
>>> for n in range(num_river):
... stations[n].testcheck()
...
<__main__.River object at 0x7fbea469bc50> 4.13
<__main__.River object at 0x7fbea46b4748> 20.76
<__main__.River object at 0x7fbea46b4320> 22.13
<__main__.River object at 0x7fbea46b4898> 16.08
So this doesn't give me the printed results that I was expecting. How can I return the string instead of the object? Will I be able to define the Class variables in this manner or will I have to list them out individually? Thanks again!
After reading many, many, many articles and tutorials on class objects I was able to come up with a solution for creating the objects using list elements.
class River():
def __init__(self, river, stage, flood, action):
self.river = river
self.stage = stage
self.action = action
self.flood = flood
self.action = action
def alerts(self):
if float(self.stage < self.flood):
#alert = "The %s is below Flood Stage (%sFt) # %s Ft. \n" % (self.river, self.flood, self.stage)
pass
elif float(self.stage > self.flood):
alert = "The %s has reached Flood Stage(%sFt) # %sFt. Warnings: %s \n" % (self.river, self.flood, self.stage, self.action)
return alert
'''this is the function that I was trying to create
to build the class objects automagically'''
def riverlist():
river_list = []
for n in range(len(rivers)):
station = River(river[n], stages[n], floods[n], warns[n])
river_list.append(station)
return river_list
if __name__ == '__main__':
for x in riverlist():
print(x.alerts())

Last page not showing in scrapy

So my code (pasted) below almost does what I want. Instead, it covers 29/30 pages, and then leaves out the last. Furthermore, I would preferably have it go beyond, but the website has no button for it (the pages actually do work when you manually fill in page=31 in the link). When Depth_Limit is 29 it's all fine, but on 30 I get the following error in the command prompt:
File "C:\Users\Ewald\Scrapy\OB\OB\spiders\spider_OB.py", line 23, in parse
next_link = 'https://zoek.officielebekendmakingen.nl/' + s.xpath('//a[#class="volgende"]/#href').extract()[0]
IndexError: list index out of range
I've tried various approaches, but they all seem to fail me...
class OB_Crawler(CrawlSpider):
name = 'OB5'
allowed_domains = ["https://www.officielebekendmakingen.nl/"]
start_urls = ["https://zoek.officielebekendmakingen.nl/zoeken/resultaat/?zkt=Uitgebreid&pst=Tractatenblad|Staatsblad|Staatscourant|BladGemeenschappelijkeRegeling|ParlementaireDocumenten&vrt=Cybersecurity&zkd=InDeGeheleText&dpr=Alle&sdt=DatumPublicatie&ap=&pnr=18&rpp=10&_page=1&sorttype=1&sortorder=4"]
custom_settings = {
'BOT_NAME': 'OB-crawler',
'DEPTH_LIMIT': 30,
'DOWNLOAD_DELAY': 0.1
}
def parse(self, response):
s = Selector(response)
next_link = 'https://zoek.officielebekendmakingen.nl/' + s.xpath('//a[#class="volgende"]/#href').extract()[0]
if len(next_link):
yield self.make_requests_from_url(next_link)
posts = response.selector.xpath('//div[#class = "lijst"]/ul/li')
for post in posts:
i = TextPostItem()
i['title'] = ' '.join(post.xpath('a/#href').extract()).replace(';', '').replace(' ', '').replace('\r\n', '')
i['link'] = ' '.join(post.xpath('a/text()').extract()).replace(';', '').replace(' ', '').replace('\r\n', '')
i['info'] = ' '.join(post.xpath('a/em/text()').extract()).replace(';', '').replace(' ', '').replace('\r\n', '').replace(',', '-')
yield i
The index out of range error is the result of an incorrect xpath (you end up calling for the first item of an empty list).
change your "next_link = ... " to
next_link = 'https://zoek.officielebekendmakingen.nl/' + s.xpath('//a[contains(#class, "volgende")]/#href').extract()[0]
You need to use contains, which runs a predicate search.. filters for what you want

Resources