Scraped youtube comments amount and real amount are different - python

Im new to Python and Im trying to code a commentscraper for youtube with the most important informations, which I put in a JSON-file. But the my amount of comments and replys is not the same as on Youtube. I don't know, where my error is. I recognized, that it doesn't write any data in the files, if there are less than 20 comments, but I don't know, where I have to change something...
Example:
https://youtu.be/Re1m9O7q-9U here I get 102, but it should be 107
https://youtu.be/Q9Y5m1fQ7Fk here I get 423, but it should be 486
https://youtu.be/cMhE5BfmFkM here I get 1315, but it should be 2052
Here is the code:
class YT_Comments:
def __init__(self, api_key):
self.api_key = api_key
self.comment_int = 0
def get_video_comments(self, video_id, limit):
url = f"https://youtube.googleapis.com/youtube/v3/commentThreads?part=replies%2C%20snippet&order=relevance&videoId={video_id}&key={self.api_key}"
vid_comments = []
pc, npt = self._get_comments_per_page(url)
if limit is not None and isinstance(limit, int):
url += f"&maxResults={str(limit)}"
while (npt is not None):
nexturl = url + "&pageToken=" + npt
pc, npt = self._get_comments_per_page(nexturl)
vid_comments.append(pc)
print(self.comment_int)
print(len(vid_comments))
return vid_comments
def _get_comments_per_page(self, url):
json_url = requests.get(url)
data = json.loads(json_url.text)
page_comments = []
if "items" not in data:
return page_comments, None
item_data = data["items"]
nextPageToken = data.get("nextPageToken", None)
for item in tqdm.tqdm(item_data):
try:
kind = item["kind"]
if kind == "youtube#comment" or "youtube#commentThread":
comment_text = item["snippet"]["topLevelComment"]["snippet"]["textOriginal"]
comment_author = item["snippet"]["topLevelComment"]["snippet"]["authorDisplayName"]
author_id = item["snippet"]["topLevelComment"]["snippet"]["authorChannelId"]["value"]
comment_like_count = item["snippet"]["topLevelComment"]["snippet"]["likeCount"]
comment_date = item["snippet"]["topLevelComment"]["snippet"]["publishedAt"]
comment = {"comment_text" : comment_text,
"comment_author" : comment_author,
"comment_author_id" : author_id,
"comment_like_count" : comment_like_count,
"comment_date" : comment_date}
replies_l = []
self.comment_int += 1
try:
replies = item["replies"]["comments"]
for reply in replies:
reply_txt = reply["snippet"]["textOriginal"]
reply_author = reply["snippet"]["authorDisplayName"]
reply_author_id = reply["snippet"]["authorChannelId"]["value"]
reply_like_count = reply["snippet"]["likeCount"]
reply_date = reply["snippet"]["publishedAt"]
reply_dict = {"text" : reply_txt,
"author" : reply_author,
"author_id" : reply_author_id,
"likes" : reply_like_count,
"date" : reply_date}
replies_l.append(reply_dict)
self.comment_int +=1
except KeyError:
replies_l.append(None)
comment_dict = {
"comment": comment,
"replies": replies_l,
}
page_comments.append(comment_dict)
except KeyError:
print("No Comments")
return page_comments, nextPageToken

Related

Cant access function in OOP python

For some reason, in my fruit scraper, i cannot access anything from listify function.
I'am getting an error, for exmaple: NameError: name 'family' is not defined.
And i cant figure out what is wrong with my code - is my function is bad, or i'am doing something wrong with class ?
import requests
import json
import random
import pickle
class FruitScraper():
def __init__(self):
self.name = []
self.id = []
self.family = []
self.genus = []
self.order = []
self.carbohydrates = []
self.protein = []
self.fat = []
self.calories = []
self.sugar = []
def scrape_all_fruits(self):
data_list = []
try:
for ID in range(1, 10):
url = f'https://www.fruityvice.com/api/fruit/{ID}'
response = requests.get(url)
data = response.json()
data_list.append(data)
except:
pass
return data_list
def listify(self, stats):
alist = json.dumps(self.scrape_all_fruits())
jsonSTr = json.loads(alist)
for i in jsonSTr:
try:
self.name.append(i['name'])
self.id.append(i['id'])
self.family.append(i['family'])
self.genus.append(i['genus'])
self.order.append(i['order'])
self.carbohydrates.append(i['nutritions']['carbohydrates'])
self.protein.append(i['nutritions']['protein'])
self.fat.append(i['nutritions']['fat'])
self.calories.append(i['nutritions']['calories'])
self.sugar.append(i['nutritions']['sugar'])
except:
pass
return stats
def get_summary(self):
for i in self.listify(zip(self.fat, self.protein, self.calories, self.sugar, self.carbohydrates, self.name)):
nutr_stats = f'\nNutrients maximum statistics:\nFat: {max(self.fat)}\nProtein: {max(self.protein)}\nCarbohydrates: {max(self.carbohydrates)}\nCalories: {max(self.calories)}\nSugar: {max(self.sugar)}' \
f'\nNutrients minimum statistics:\nFat: {min(self.fat)}\nProtein: {min(self.protein)}\nCarbohydrates: {min(self.carbohydrates)}\nCalories: {min(self.calories)}\nSugar: {min(self.sugar)}' \
f'\nTotal fruits scraped: {len(self.name)}'
return nutr_stats
Scraped_info = FruitScraper().scrape_all_fruits()
Listified_info = FruitScraper().listify(family)
Fruits_statistics = FruitScraper().get_summary()
It's my first time doing OOP.

Please consider changing this
Scraped_info = FruitScraper().scrape_all_fruits()
Listified_info = FruitScraper().listify(family)
Fruits_statistics = FruitScraper().get_summary()
to
myScraper = FruitScraper()
Scraped_info = myScraper.scrape_all_fruits()
myScraper.listify()
Fruits_statistics = myScraper.get_summary()
Otherwise you create three different objects of this class and discard them with all their attributes after running the individual method once.
This might also be critical to define family in this line of the code:
Listified_info = myScraper.listify(family)
But I can't see how you intended to use the parameter stats in your method listify(). It is just received and returned. I suggest that you change:
def listify(self, stats):
to
def listify(self):
and remove
return stats
If you want to get those lists inside the object of this class returned by listify(), you may do the following (but this is not OOP way of doing things):
import requests
import json
import copy
class FruitScraper():
def __init__(self):
self.name = []
self.id = []
self.family = []
self.genus = []
self.order = []
self.carbohydrates = []
self.protein = []
self.fat = []
self.calories = []
self.sugar = []
def collect_all_lists(self):
self.allLists = dict('name': self.name, 'id': self.id, 'family': self.family, 'genus': self.genus, 'order': self.order, 'carbohydrates': self.carbohydrates, 'protein': self.protein, 'fat': self.fat, 'calories': self.calories, 'sugar': self.sugar)
def scrape_all_fruits(self):
data_list = []
try:
for ID in range(1, 10):
url = f'https://www.fruityvice.com/api/fruit/{ID}'
response = requests.get(url)
data = response.json()
data_list.append(data)
except:
pass
return data_list
def listify(self):
alist = json.dumps(self.scrape_all_fruits())
jsonSTr = json.loads(alist)
for i in jsonSTr:
try:
self.name.append(i['name'])
self.id.append(i['id'])
self.family.append(i['family'])
self.genus.append(i['genus'])
self.order.append(i['order'])
self.carbohydrates.append(i['nutritions']['carbohydrates'])
self.protein.append(i['nutritions']['protein'])
self.fat.append(i['nutritions']['fat'])
self.calories.append(i['nutritions']['calories'])
self.sugar.append(i['nutritions']['sugar'])
except:
pass
self.collect_all_lists()
return copy.deepcopy(self.allLists)
def get_summary(self):
for i in self.listify(zip(self.fat, self.protein, self.calories, self.sugar, self.carbohydrates, self.name)):
nutr_stats = f'\nNutrients maximum statistics:\nFat: {max(self.fat)}\nProtein: {max(self.protein)}\nCarbohydrates: {max(self.carbohydrates)}\nCalories: {max(self.calories)}\nSugar: {max(self.sugar)}' \
f'\nNutrients minimum statistics:\nFat: {min(self.fat)}\nProtein: {min(self.protein)}\nCarbohydrates: {min(self.carbohydrates)}\nCalories: {min(self.calories)}\nSugar: {min(self.sugar)}' \
f'\nTotal fruits scraped: {len(self.name)}'
return nutr_stats
myScraper = FruitScraper()
Scraped_info = myScraper.scrape_all_fruits()
Listified_info = myScraper.listify()
Fruits_statistics = myScraper.get_summary()

Parsing logs to json Python

Folks,
I am trying to parse log file into json format.
I have a lot of logs, there is one of them
How can I parse this?
03:02:03.113 [info] ext_ref = BANK24AOS_cl_reqmarketcreditorderstate_6M8I1NT8JKYD_1591844522410384_4SGA08M8KIXQ reqid = 1253166 type = INREQ channel = BANK24AOS sid = msid_1591844511335516_KRRNBSLH2FS duration = 703.991 req_uri = marketcredit/order/state login = 77012221122 req_type = cl_req req_headers = {"accept-encoding":"gzip","connection":"close","host":"test-mobileapp-api.bank.kz","user-agent":"okhttp/4.4.1","x-forwarded-for":"212.154.169.134","x-real-ip":"212.154.169.134"} req_body = {"$sid":"msid_1591844511335516_KRRNBSLH2FS","$sid":"msid_1591844511335516_KRRNBSLH2FS","app":"bank","app_version":"2.3.2","channel":"aos","colvir_token":"GExPR0lOX1BBU1NXT1JEX0NMRUFSVEVYVFNzrzh4Thk1+MjDKWl/dDu1fQPsJ6gGLSanBp41yLRv","colvir_commercial_id":"-1","colvir_id":"000120.335980","openway_commercial_id":"6247520","openway_id":"6196360","$lang":"ru","ekb_id":"923243","inn":"990830221722","login":"77012221122","bank24_id":"262"} resp_body = {"task_id":"","status":"success","data":{"state":"init","applications":[{"status":"init","id":"123db561-34a3-4a8d-9fa7-03ed6377b44f","name":"Sulpak","amount":101000,"items":[{"name":"Switch CISCO x24","price":100000,"count":1,"amount":100000}]}],"segment":{"range":{"min":6,"max":36,"step":1},"payment_day":{"max":28,"min":1}}}}
Into this type of json, or any other format (but I guess json is best one)
{
"time":"03:02:03.113",
"class_req":"info",
"ext_ref":"BANK24AOS_cl_reqmarketcreditorderstate_6M8I1NT8JKYD_1591844522410384_4SGA08M8KIXQ",
"reqid":"1253166",
"type":"INREQ",
"channel":"BANK24AOS",
"sid":"msid_1591844511335516_KRRNBSLH2FS",
"duration":"703.991",
"req_uri":"marketcredit/order/state",
"login":"77012221122",
"req_type":"cl_req",
"req_headers":{
"accept-encoding":"gzip",
"connection":"close",
"host":"test-mobileapp-api.bank.kz",
"user-agent":"okhttp/4.4.1",
"x-forwarded-for":"212.154.169.134",
"x-real-ip":"212.154.169.134"
},
"req_body":{
"$sid":"msid_1591844511335516_KRRNBSLH2FS",
"$sid":"msid_1591844511335516_KRRNBSLH2FS",
"app":"bank",
"app_version":"2.3.2",
"channel":"aos",
"colvir_token":"GExPR0lOX1BBU1NXT1JEX0NMRUFSVEVYVFNzrzh4Thk1+MjDKWl/dDu1fQPsJ6gGLSanBp41yLRv",
"colvir_commercial_id":"-1",
"colvir_id":"000120.335980",
"openway_commercial_id":"6247520",
"openway_id":"6196360",
"$lang":"ru",
"ekb_id":"923243",
"inn":"990830221722",
"login":"77012221122",
"bank24_id":"262"
},
"resp_body":{
"task_id":"",
"status":"success",
"data":{
"state":"init",
"applications":[
{
"status":"init",
"id":"123db561-34a3-4a8d-9fa7-03ed6377b44f",
"name":"Sulpak",
"amount":101000,
"items":[
{
"name":"Switch CISCO x24",
"price":100000,
"count":1,
"amount":100000
}
]
}
],
"segment":{
"range":{
"min":6,
"max":36,
"step":1
},
"payment_day":{
"max":28,
"min":1
}
}
}
}
}
I am trying to split first whole text, but there I met another problem is to match keys to values depending on '=' sign. Also there might be some keys with empty values. For ex.:
type = INREQ channel = sid = duration = 1.333 (to get to know that there is an empty value, you need to pay attention on number of spaces. Usually there is 1 space between prev.value and next key). So this example should look like this:
{
"type":"INREQ",
"channel":"",
"sid":"",
"duration":"1.333"
}
Thanks ahead!

Here, one thing pass for duplicate key about "$sid":"msid_1591844511335516_KRRNBSLH2FS"
import re
text = """03:02:03.113 [info] ext_ref = reqid = 1253166 type = INREQ channel = BANK24AOS sid = msid_1591844511335516_KRRNBSLH2FS duration = 703.991 req_uri = marketcredit/order/state login = 77012221122 req_type = cl_req req_headers = {"accept-encoding":"gzip","connection":"close","host":"test-mobileapp-api.bank.kz","user-agent":"okhttp/4.4.1","x-forwarded-for":"212.154.169.134","x-real-ip":"212.154.169.134"} req_body = {"$sid":"msid_1591844511335516_KRRNBSLH2FS","$sid":"msid_1591844511335516_KRRNBSLH2FS","app":"bank","app_version":"2.3.2","channel":"aos","colvir_token":"GExPR0lOX1BBU1NXT1JEX0NMRUFSVEVYVFNzrzh4Thk1+MjDKWl/dDu1fQPsJ6gGLSanBp41yLRv","colvir_commercial_id":"-1","colvir_id":"000120.335980","openway_commercial_id":"6247520","openway_id":"6196360","$lang":"ru","ekb_id":"923243","inn":"990830221722","login":"77012221122","bank24_id":"262"} resp_body = {"task_id":"","status":"success","data":{"state":"init","applications":[{"status":"init","id":"123db561-34a3-4a8d-9fa7-03ed6377b44f","name":"Sulpak","amount":101000,"items":[{"name":"Switch CISCO x24","price":100000,"count":1,"amount":100000}]}],"segment":{"range":{"min":6,"max":36,"step":1},"payment_day":{"max":28,"min":1}}}}"""
index1 = text.index('[')
index2 = text.index(']')
new_text = 'time = '+ text[:index1-1] + ' class_req = ' + text[index1+1:index2] + text[index2+2:]
lst = re.findall(r'\S+? = |\S+? = \{.*?\} |\S+? = \{.*?\}$|\S+? = \S+? ', new_text)
res = {}
for item in lst:
key, equal, value = item.partition('=')
key, value = key.strip(), value.strip()
if value.startswith('{'):
try:
value = json.loads(value)
except:
print(value)
res[key] = value

you can try regulation in python.
here is what i write, it works for your problem.
for convenience i deleted string before "ext_ref...",you can directly truncate the raw string.
import re
import json
string = 'ext_ref = BANK24AOS_cl_reqmarketcreditorderstate_6M8I1NT8JKYD_1591844522410384_4SGA08M8KIXQ reqid = 1253166 type = INREQ channel = BANK24AOS sid = msid_1591844511335516_KRRNBSLH2FS duration = 703.991 req_uri = marketcredit/order/state login = 77012221122 req_type = cl_req req_headers = {"accept-encoding":"gzip","connection":"close","host":"test-mobileapp-api.bank.kz","user-agent":"okhttp/4.4.1","x-forwarded-for":"212.154.169.134","x-real-ip":"212.154.169.134"} req_body = {"$sid":"msid_1591844511335516_KRRNBSLH2FS","$sid":"msid_1591844511335516_KRRNBSLH2FS","app":"bank","app_version":"2.3.2","channel":"aos","colvir_token":"GExPR0lOX1BBU1NXT1JEX0NMRUFSVEVYVFNzrzh4Thk1+MjDKWl/dDu1fQPsJ6gGLSanBp41yLRv","colvir_commercial_id":"-1","colvir_id":"000120.335980","openway_commercial_id":"6247520","openway_id":"6196360","$lang":"ru","ekb_id":"923243","inn":"990830221722","login":"77012221122","bank24_id":"262"} resp_body = {"task_id":"","status":"success","data":{"state":"init","applications":[{"status":"init","id":"123db561-34a3-4a8d-9fa7-03ed6377b44f","name":"Sulpak","amount":101000,"items":[{"name":"Switch CISCO x24","price":100000,"count":1,"amount":100000}]}],"segment":{"range":{"min":6,"max":36,"step":1},"payment_day":{"max":28,"min":1}}}}'
position = re.search("req_headers",string) # position of req_headers
resp_body_pos = re.search("resp_body",string)
resp_body = string[resp_body_pos.span()[0]:]
res1 = {}
res1.setdefault(resp_body.split("=")[0],resp_body.split("=")[1])
print(res1)
before = string[:position.span()[0]]
after = string[position.span()[0]:resp_body_pos.span()[0]] # handle req_body seperately
res2 = re.findall("(\S+) = (\S+)",before)
print(res2)
res3 = re.findall("(\S+) = ({.*?})",after)
print(res3)
#res1 type: dict{'resp_body':'...'} content in resp_body
#res2 type: list[(),()..] content before req_head
#res3 type: list[(),()..] the rest content
and now you can do what you want to do with the data(.e.g. transform it into json respectively)
Hope this is helpful

Scraping view function remembers its previous iterations

I have the following view function used to scrape data:
def results(request):
if request.method == 'POST':
form = RoomForm(request.POST)
if form.is_valid():
form_city = form.cleaned_data['city'].title()
form_country = form.cleaned_data['country'].title()
form_arrival_date = form.cleaned_data['arrival_date']
form_departure_date = form.cleaned_data['departure_date']
form_pages_to_scrape = form.cleaned_data['pages_to_scrape']
#launch scraper
scraper = AIRBNB_scraper(city=form_city, country=form_country, arrival_date=str(form_arrival_date), departure_date=str(form_departure_date))
scraped_dataframe = scraper.scrape_multiple_pages(last_page_selector_number=form_pages_to_scrape)
scraped_dataframe_sorted = scraped_dataframe.sort_values('prices')
print(scraped_dataframe_sorted)
#convert scraped dataframe into lists
prices = scraped_dataframe_sorted['prices'].tolist()
listings_links = scraped_dataframe_sorted['listings_links'].tolist()
listings_names = scraped_dataframe_sorted['listings_names'].tolist()
photo_links = scraped_dataframe_sorted['photo_links'].tolist()
dictionary = zip(prices, listings_links, listings_names, photo_links)
context = {'dictionary': dictionary}
return render(request, 'javascript/results.html', context)
On form submit, a post request is sent to this function using AJAX:
var frm = $('#login-form');
frm.submit(function () {
$.ajax({
type: "POST",
url: "/results",
data: frm.serialize(),
success: function (data) {
$("#table").html(data);
$('#go_back').remove();
},
error: function(data) {
$("#table").html("Something went wrong!");
}
});
return false;
});
After that the scraped data is displayed as HTML table on the same page the form is on.
The problem is the number of scraped items doubles every time the form submit is done. So for example if the number of scraped items on first button click is sixteen, the output will be 16, but on the second run it will be 32, then 64, and so on.
It is like the app remembers previous form submits, but I don't see any reason why. I tried clearin - at the end of this function - the pandas dataframe used to store the scraped data and also the dictionary passed as context, but to no avail.
The form is:
class RoomForm(forms.Form):
city = forms.CharField(max_length=100)
country = forms.CharField(max_length=100)
arrival_date = forms.DateField(widget=forms.DateInput(attrs=
{
'class':'datepicker'
}), required=False)
departure_date = forms.DateField(widget=forms.DateInput(attrs=
{
'class':'datepicker'
}), required=False)
pages_to_scrape = forms.IntegerField(label='Pages to scrape (max. 17)', min_value=0, max_value=17, widget=forms.NumberInput(attrs={'style':'width: 188px'}))
AIRBNB_scraper is:
import requests, bs4
import re
import pandas as pd
price_pattern = re.compile(r'\d*\s*?,?\s*?\d*\szł')
photo_link_pattern = re.compile(r'https.*\)')
prices = []
listings_links = []
photo_links = []
listings_names = []
class AIRBNB_scraper():
def __init__(self, city, country, accomodation_type='homes', arrival_date='2018-03-25', departure_date='2018-04-10'):
self.city = city
self.country = country
self.arrival_date = arrival_date
self.departure_date = departure_date
self.accomodation_type = accomodation_type
def make_soup(self, page_number):
url = 'https://www.airbnb.pl/s/'+ self.city +'--'+ self.country +'/'+ self.accomodation_type +'?query='+ self.city +'%2C%20'+ self.country +'&refinement_paths%5B%5D=%2F'+ self.accomodation_type +'&checkin=' + self.arrival_date + '&checkout=' + self.departure_date + '&section_offset=' + str(page_number)
response = requests.get(url)
soup = bs4.BeautifulSoup(response.text, "html.parser")
return soup
def get_listings(self, page_number):
soup = self.make_soup(page_number)
listings = soup.select('._f21qs6')
number_of_listings = len(listings)
print('\n' + "Number of listings found: " + str(number_of_listings))
while number_of_listings != 18:
print('\n' + str(number_of_listings) + ' is not correct number of listings, it should be 18. Trying again now.')
soup = self.make_soup(page_number)
listings = soup.find_all('div', class_='_f21qs6')
number_of_listings = len(listings)
print('\n' + "All fine! The number of listings is: " + str(number_of_listings) + '. Starting scraping now')
return listings
def scrape_listings_per_page(self, page_number):
listings_to_scrape = self.get_listings(page_number)
for listing in listings_to_scrape:
#get price
price_container = listing.find_all('span', class_='_hylizj6')
price_search = re.search(price_pattern, str(price_container))
price = price_search.group()
#get listing_link
listing_link = 'https://www.airbnb.pl' + listing.find('a', class_='_15ns6vh')['href']
#get photo_link
photo_link_node = listing.find('div', class_="_1df8dftk")['style']
photo_link_search = re.search(photo_link_pattern, str(photo_link_node))
#~ if photo_link_search:
#~ print('Is regex match')
#~ else:
#~ print('No regex match')
photo_link_before_strip = photo_link_search.group()
photo_link = photo_link_before_strip[:-1] #remove ") at the end of link
#get listing_name
listing_name = listing.find('div', class_='_1rths372').text
#append lists
prices.append(price)
listings_links.append(listing_link)
photo_links.append(photo_link)
listings_names.append(listing_name)
def scrape_multiple_pages(self, last_page_selector_number):
last_page_selector_number += 1
for x in range(0, last_page_selector_number):#18
self.scrape_listings_per_page(x)
print('\n' + "INDEX OF PAGE BEING SCRAPED: " + str(x))
scraped_data = pd.DataFrame({'prices': prices,
'listings_links': listings_links,
'photo_links': photo_links,
'listings_names': listings_names})
return scraped_data

You have module-level variables: prices, listings_links, etc. You append to these inside your AIRBNB_scraper instance but they are not part of that instance, and will persist between calls. You should make them instance attributes - define them as self.prices etc in the __init__ method.

Proper way to format date for Fedex API XML

I have a Django application where I am trying to make a call to Fedex's API to send out a shipping label for people wanting to send in a product for cash. When I try to make the call though it says there is a data validation issue with the Expiration field in the XML I am filling out. I swear this has worked in the past with me formatting the date as "YYYY-MM-DD", but now it is not. I read that with Fedex, you need to format the date as ISO, but that is also not passing the data validation. I am using a python package created to help with tapping Fedex's API.
Django view function for sending API Call
def Fedex(request, quote):
label_link = ''
expiration_date = datetime.datetime.now() + datetime.timedelta(days=10)
# formatted_date = "%s-%s-%s" % (expiration_date.year, expiration_date.month, expiration_date.day)
formatted_date = expiration_date.replace(microsecond=0).isoformat()
if quote.device_type != 'laptop':
box_length = 9
box_width = 12
box_height = 3
else:
box_length = 12
box_width = 14
box_height = 3
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
## Page 411 of FedEx Dev Guide - 20.14 Email Labels
CONFIG_OBJ = FedexConfig(key=settings.FEDEX_KEY, password=settings.FEDEX_PASSWORD, account_number=settings.FEDEX_ACCOUNT,
meter_number=settings.FEDEX_METER, use_test_server=settings.USE_FEDEX_TEST)
fxreq = FedexCreatePendingShipRequestEmail(CONFIG_OBJ, customer_transaction_id='xxxxxx id:01')
fxreq.RequestedShipment.ServiceType = 'FEDEX_GROUND'
fxreq.RequestedShipment.PackagingType = 'YOUR_PACKAGING'
fxreq.RequestedShipment.DropoffType = 'REGULAR_PICKUP'
fxreq.RequestedShipment.ShipTimestamp = datetime.datetime.now()
# Special fields for the email label
fxreq.RequestedShipment.SpecialServicesRequested.SpecialServiceTypes = ('RETURN_SHIPMENT', 'PENDING_SHIPMENT')
fxreq.RequestedShipment.SpecialServicesRequested.PendingShipmentDetail.Type = 'EMAIL'
fxreq.RequestedShipment.SpecialServicesRequested.PendingShipmentDetail.ExpirationDate = formatted_date
email_address = fxreq.create_wsdl_object_of_type('EMailRecipient')
email_address.EmailAddress = quote.email
email_address.Role = 'SHIPMENT_COMPLETOR'
# RETURN SHIPMENT DETAIL
fxreq.RequestedShipment.SpecialServicesRequested.ReturnShipmentDetail.ReturnType = ('PENDING')
fxreq.RequestedShipment.SpecialServicesRequested.ReturnShipmentDetail.ReturnEMailDetail = fxreq.create_wsdl_object_of_type(
'ReturnEMailDetail')
fxreq.RequestedShipment.SpecialServicesRequested.ReturnShipmentDetail.ReturnEMailDetail.MerchantPhoneNumber = 'x-xxx-xxx-xxxx'
fxreq.RequestedShipment.SpecialServicesRequested.PendingShipmentDetail.EmailLabelDetail.Recipients = [email_address]
fxreq.RequestedShipment.SpecialServicesRequested.PendingShipmentDetail.EmailLabelDetail.Message = "Xxxxxx Xxxxxx"
fxreq.RequestedShipment.LabelSpecification = {'LabelFormatType': 'COMMON2D', 'ImageType': 'PDF'}
fxreq.RequestedShipment.Shipper.Contact.PersonName = quote.first_name + ' ' + quote.last_name
fxreq.RequestedShipment.Shipper.Contact.CompanyName = ""
fxreq.RequestedShipment.Shipper.Contact.PhoneNumber = quote.phone
fxreq.RequestedShipment.Shipper.Address.StreetLines.append(quote.address)
fxreq.RequestedShipment.Shipper.Address.City = quote.city
fxreq.RequestedShipment.Shipper.Address.StateOrProvinceCode = quote.state
fxreq.RequestedShipment.Shipper.Address.PostalCode = quote.zip
fxreq.RequestedShipment.Shipper.Address.CountryCode = settings.FEDEX_COUNTRY_CODE
fxreq.RequestedShipment.Recipient.Contact.PhoneNumber = settings.FEDEX_PHONE_NUMBER
fxreq.RequestedShipment.Recipient.Address.StreetLines = settings.FEDEX_STREET_LINES
fxreq.RequestedShipment.Recipient.Address.City = settings.FEDEX_CITY
fxreq.RequestedShipment.Recipient.Address.StateOrProvinceCode = settings.FEDEX_STATE_OR_PROVINCE_CODE
fxreq.RequestedShipment.Recipient.Address.PostalCode = settings.FEDEX_POSTAL_CODE
fxreq.RequestedShipment.Recipient.Address.CountryCode = settings.FEDEX_COUNTRY_CODE
fxreq.RequestedShipment.Recipient.AccountNumber = settings.FEDEX_ACCOUNT
fxreq.RequestedShipment.Recipient.Contact.PersonName = ''
fxreq.RequestedShipment.Recipient.Contact.CompanyName = 'Xxxxxx Xxxxxx'
fxreq.RequestedShipment.Recipient.Contact.EMailAddress = 'xxxxxx#xxxxxxxxx'
# Details of Person Who is Paying for the Shipping
fxreq.RequestedShipment.ShippingChargesPayment.PaymentType = 'SENDER'
fxreq.RequestedShipment.ShippingChargesPayment.Payor.ResponsibleParty.AccountNumber = settings.FEDEX_ACCOUNT
fxreq.RequestedShipment.ShippingChargesPayment.Payor.ResponsibleParty.Contact.PersonName = 'Xxxxx Xxxxx'
fxreq.RequestedShipment.ShippingChargesPayment.Payor.ResponsibleParty.Contact.CompanyName = 'Xxxxx Xxxxxx'
fxreq.RequestedShipment.ShippingChargesPayment.Payor.ResponsibleParty.Contact.PhoneNumber = 'x-xxx-xxx-xxxx'
fxreq.RequestedShipment.ShippingChargesPayment.Payor.ResponsibleParty.Contact.EMailAddress = 'xxxxxxx#xxxxxxxxx'
fxreq.RequestedShipment.ShippingChargesPayment.Payor.ResponsibleParty.Address.StreetLines = 'Xxxxx N. xXxxxxx'
fxreq.RequestedShipment.ShippingChargesPayment.Payor.ResponsibleParty.Address.City = 'Xxxxxxx'
fxreq.RequestedShipment.ShippingChargesPayment.Payor.ResponsibleParty.Address.StateOrProvinceCode = 'XX'
fxreq.RequestedShipment.ShippingChargesPayment.Payor.ResponsibleParty.Address.PostalCode = 'xxxxx'
fxreq.RequestedShipment.ShippingChargesPayment.Payor.ResponsibleParty.Address.CountryCode = 'US'
# Package Info
package1 = fxreq.create_wsdl_object_of_type('RequestedPackageLineItem')
package1.SequenceNumber = '1'
package1.Weight.Value = 1
package1.Weight.Units = "LB"
package1.Dimensions.Length = box_length
package1.Dimensions.Width = box_width
package1.Dimensions.Height = box_height
package1.Dimensions.Units = "IN"
package1.ItemDescription = 'Phone'
fxreq.RequestedShipment.RequestedPackageLineItems.append(package1)
fxreq.RequestedShipment.PackageCount = '1'
try:
fxreq.send_request()
label_link = str(fxreq.response.CompletedShipmentDetail.AccessDetail.AccessorDetails[0].EmailLabelUrl)
except Exception as exc:
print('Fedex Error')
print('===========')
print(exc)
print('==========')
return label_link
Error Log
Error:cvc-datatype-valid.1.2.1: \\'2017-11-3\\' is not a valid value for \\'date\\'.\\ncvc-type.3.1.3: The value \\'2017-11-3\\' of element \\'ns0:ExpirationDate\\' is not valid."\\n }\\n }' (Error code: -1)

Appending a python dict from a while loop gives unexpected results

The max number of records in my input json is 100 however there is a paging-next link that provides the next 100 records. Below is what I have but it returns a dict with only 100 entries- I know there are more- How should I modify this function to get all the records?
def process_comment_json(comment_json):
post_comment_dict = dict()
next_links = list()
if 'comments' in comment_json.keys():
try:
for y in comment_json['comments']['data']:
post_id = comment_json['id']
commentor_name = y['from']['name']
commentor_id = y['from']['id']
created_time = y['created_time']
message = remove_non_ascii(y['message'])
sentiment = return_sentiment_score(message)
post_comment_dict[commentor_id] = {'commentor_name':commentor_name,\
'created_time':created_time, 'message':message,\
'sentiment':sentiment}
except:
print("malformed data, skipping this comment in round1")
if 'next' in comment_json['comments']['paging']:
print('found_next appending')
next_links.append(comment_json['comments']['paging']['next'])
else:
return post_comment_dict
while next_links:
print("processing next_links")
print("current len of post_comment_dict is:", len(post_comment_dict))
for next_link in next_links:
t = requests.get(next_link)
nl_json = t.json()
next_links.pop()
if "data" in list(nl_json.keys()):
for record in nl_json['data']:
try:
for y in comment_json['comments']['data']:
post_id = comment_json['id']
commentor_name = y['from']['name']
commentor_id = y['from']['id']
created_time = y['created_time']
message = remove_non_ascii(y['message'])
sentiment = return_sentiment_score(message)
post_comment_dict[commentor_id] = {'commentor_name':commentor_name,\
'created_time':created_time, 'message':message,\
'sentiment':sentiment}
except:
print("malformed data, skipping this comment from the next_links list")
if 'next' in comment_json['comments']['paging']:
print('found_next appending')
next_links.append(comment_json['comments']['paging']['next'])
else:
return post_comment_dict

Categories