Problems retrieving information from imdb - python

I'm trying to get the movie titles from an imdb watchlist. This is my code:
import requests, bs4
res = requests.get(url)
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text, "html.parser")
print(soup.find_all('.lister-item-header'))
Even though '.lister-item-header' exists in the chrome developer console it doesn't exist in the html file that the requests module downloaded. I've also tried using regular expressions. What would be the best way of retrieving the titles?

You should select elements by their class in this way.
import requests
import bs4
url = 'http://www.imdb.com/chart/top'
res = requests.get(url)
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text, "html.parser")
rows = soup.select('.titleColumn > a')
for row in rows:
print(row.text)
Or you can do it in this way:
import requests
import bs4
url = 'http://www.imdb.com/chart/top'
res = requests.get(url)
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text, "html.parser")
rows = soup.find_all('td', class_='titleColumn')
for row in rows:
print(row.a.text)
The data is load from a json object which is embedded into the raw html file, so we can parse it and get the title.
import requests
import bs4
import json
url = 'http://www.imdb.com/user/ur69187878/watchlist?ref_=wt_nv_wl‌​_all_1'
res = requests.get(url)
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text, "html.parser")
# rows = soup.find_all('h3', class_='list-item-header')
js_elements = soup.find_all('script')
js_text = None
search_str = 'IMDbReactInitialState.push('
for element in js_elements:
text = element.text
if search_str in text:
js_text = text.strip()
break
json_start = js_text.index(search_str) + len(search_str)
json_text = js_text[json_start:-2]
json_obj = json.loads(js_text[json_start:-2])
for title in json_obj['titles']:
json_title = json_obj['titles'][title]
print(json_title['primary']['title'])
But I have to say that this is not a general method to attack this kind of problems, if you wanna have a general solution for all pages whose data is loaded from json or api, you can use some other ways such as Selenium.

Related

Get data from bs4 script

I am new to programming and i am trying to parse this page: https://ruz.spbstu.ru/faculty/100/groups
url = "https://ruz.spbstu.ru/faculty/100/groups"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
scripts = soup.find_all('script')
print(scripts[3].text)
this gives me
window.__INITIAL_STATE__ = {"faculties":{"isFetching":false,"data":null,"errors":null},"groups":{"isFetching":false,"data":{"100":[{"id":35754,"name":"3733806/00301","level":3,"type":"common","kind":0,"spec":"38.03.06 Торговое дело","year":2022},{"id":35715,"name":"3763801/10103","level":2,"type":"common","kind":3,"spec":"38.06.01 Экономика","year":2022},{"id":34725,"name":"з3753801/80430_2021","level":5,"type":"distance","kind":2,"spec":"38.05.01 Экономическая безопасность","year":2022},{"id":33632,"name":"3733801/10002_2021","level":2,"type":"common","kind":0,"spec":"38.03.01 Экономика","year":2022}...........
contents are very long so this is an extract from the output.
i need get all 'id's and 'name's from this output and put them into the dictionary like {id:name}, i can't figure out a way how to do it.
Any information will be very helpful.
Try:
import re
import json
import requests
from bs4 import BeautifulSoup
url = "https://ruz.spbstu.ru/faculty/100/groups"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
scripts = soup.find_all("script")
data = re.search(r".*?({.*});", scripts[3].text).group(1)
data = json.loads(data)
out = {d["id"]: d["name"] for d in data["groups"]["data"]["100"]}
print(out)
Prints:
{35754: '3733806/00301', 35715: '3763801/10103', ...etc.

Beautifulsoup findAll returns an empty list

I'm trying to scrape a webpage using beautifulsoup, but findAll() returns an empty list. This is my code:
URL = "https://elcinema.com/en/index/work/country/eg?page=1"
r = requests.get(URL)
bsObj = BeautifulSoup(r.content, 'html5lib')
recordList = bsObj.findAll('a', attrs = {'class':"lazy-loaded "})
print(recordList)
What am I doing wrong?
you need to find img tags with a class lazyloaded
import requests
from bs4 import BeautifulSoup
URL = "https://elcinema.com/en/index/work/country/eg?page=1"
r = requests.get(URL)
bsObj = BeautifulSoup(r.content, 'html')
recordList = bsObj.findAll('img',class_="lazy-loaded")
recordList =[i['data-src'] for i in recordList ]
print(recordList)
Output:
['https://media.elcinema.com/blank_photos/75x75.jpg', 'https://media.elcinema.com/uploads/_75x75_2fe90cb32f2759181f71eb2a9b29f0735f87ac88150a6a8fd3734300f8714369.jpg', 'https://media.elcinema.com/uploads/_75x75_3d90d1ee22c5f455bc4556073eab69cd218446d6134dc0f2694782ee39ccb5bf.jpg', 'https://media.elcinema.com/uploads/_75x75_81f30061ed82645e9ee688642275d76a23ee329344c5ac25c42f22afa35432ff.jpg', 'https://media.elcinema.com/blank_photos/75x75.jpg',.......]
According to the question, it looks like you need to find all a records who have img tag in it with a specific class lazy-loaded Follow the below code to get those:
Code:
import requests
from bs4 import BeautifulSoup
URL = "https://elcinema.com/en/index/work/country/eg?page=1"
r = requests.get(URL)
bsObj = BeautifulSoup(r.content, 'html.parser')
outputdata=[]
recordList = bsObj.findAll('a')
for record in recordList:
if record.find("img",{"class":"lazy-loaded"}):
outputdata.append(record)
print(len(outputdata))
print(outputdata)
Output:
Let me know if you have any questions :)

Retrieving content using Beautifulsoup and selectors

Trying to retrieve content (text) embedded in html. Not getting the content.
Trying to use selector in the format to find price_box:
price_box = soup2.find('div', attrs={'title class': 'Fw(600)'})
# Import libraries
import requests
import urllib.request
import time
from bs4 import BeautifulSoup
# Set the URL you want to webscrape from
url = 'https://finance.yahoo.com/quote/NVDA?p=NVDA'
# Connect to the URL
response = requests.get(url)
# Parse HTML and save to BeautifulSoup object¶
soup = BeautifulSoup(response.text, "html.parser")
beta = soup.find('h1')
#print (beta)
link = beta.contents
variable = 'NVDA - NVIDIA Corporation'
test = 'NVDA - NVIDIA Corporation'
#<..>
url2 = 'https://finance.yahoo.com/calendar/earnings?from=2019-09-01&to=2019-09-07&day=2019-09-01'
response2 = requests.get(url2)
soup2 = BeautifulSoup(response2.text, "html.parser")
# alpha = soup2.find('')
# div = soup.find('a', {class_ ='D(ib) '})
# text = div.string
price_box = soup2.find('div', attrs={'title class': 'Fw(600)'})
#price = price_box.text
print("Price Box: "+ str(price_box)) # THIS IS WHAT I WANT
Was hoping to see "Senea". Instead seeing "None" - "Price Box:
None"
A lot of the content is dynamic. You can regex out that info easily
import requests, re
p = re.compile(r'"YFINANCE:(.*?)"')
r = requests.get('https://finance.yahoo.com/calendar/earnings?from=2019-09-01&to=2019-09-07&day=2019-09-01&guccounter=1')
print(p.findall(r.text)[0])
An alternate is to avoid the dynamic looking classes altogether
import requests
from bs4 import BeautifulSoup as bs
r = requests.get('https://finance.yahoo.com/calendar/earnings?from=2019-09-01&to=2019-09-07&day=2019-09-01&guccounter=1')
soup = bs(r.content, 'lxml')
print(soup.select_one('#cal-res-table a').text)
Reading:
css selectors

How do I simultaneously scrape two pages and produce two distinct lists within one nested 'for-loop'?

I'm scraping from two URLs that have the same DOM structure, and so I'm trying to find a way to scrape both of them at the same time.
The only caveat is that the data scraped from both these pages need to end up on distinctly named lists.
To explain with example, here is what I've tried:
import os
import requests
from bs4 import BeautifulSoup as bs
urls = ['https://www.basketball-reference.com/leaders/ws_career.html',
'https://www.basketball-reference.com/leaders/ws_per_48_career.html',]
ws_list = []
ws48_list = []
categories = [ws_list, ws48_list]
for url in urls:
response = requests.get(url, headers=headers)
soup = bs(response.content, 'html.parser')
section = soup.find('table', class_='stats_table')
for a in section.find_all('a'):
player_name = a.text
for cat_list in categories:
cat_list.append(player_name)
print(ws48_list)
print(ws_list)
This ends up printing two identical lists when I was shooting for 2 lists unique to its page.
How do I accomplish this? Would it be better practice to code it another way?
Instead of trying to append to already existing lists. Just create new ones. Make a function to do the scrape and pass each url in turn to it.
import os
import requests
from bs4 import BeautifulSoup as bs
urls = ['https://www.basketball-reference.com/leaders/ws_career.html',
'https://www.basketball-reference.com/leaders/ws_per_48_career.html',]
def parse_page(url, headers={}):
response = requests.get(url, headers=headers)
soup = bs(response.content, 'html.parser')
section = soup.find('table', class_='stats_table')
return [a.text for a in section.find_all('a')]
ws_list, ws48_list = [parse_page(url) for url in urls]
print('ws_list = %r' % ws_list)
print('ws8_list = %r' % ws48_list)
Just add them to the appropriate list and the problem is solved?
for i, url in enumerate(urls):
response = requests.get(url)
soup = bs(response.content, 'html.parser')
section = soup.find('table', class_='stats_table')
for a in section.find_all('a'):
player_name = a.text
categories[i].append(player_name)
print(ws48_list)
print(ws_list)
You can use a function to define your scraping logic, then just call it for your urls.
import os
import requests
from bs4 import BeautifulSoup as bs
def scrape(url):
response = requests.get(url)
soup = bs(response.content, 'html.parser')
section = soup.find('table', class_='stats_table')
names = []
for a in section.find_all('a'):
player_name = a.text
names.append(player_name)
return names
ws_list = scrape('https://www.basketball-reference.com/leaders/ws_career.html')
ws48_list = scrape('https://www.basketball-reference.com/leaders/ws_per_48_career.html')
print(ws_list)
print(ws48_list)

Scrape Multiple URLs using Beautiful Soup

I'm trying to extract specific classes from multiple URLs. The tags and classes stay the same but I need my python program to scrape all as I just input my link.
Here's a sample of my work:
from bs4 import BeautifulSoup
import requests
import pprint
import re
import pyperclip
url = input('insert URL here: ')
#scrape elements
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
#print titles only
h1 = soup.find("h1", class_= "class-headline")
print(h1.get_text())
This works for individual URLs but not for a batch. Thanks for helping me. I learned a lot from this community.
Have a list of urls and iterate through it.
from bs4 import BeautifulSoup
import requests
import pprint
import re
import pyperclip
urls = ['www.website1.com', 'www.website2.com', 'www.website3.com', .....]
#scrape elements
for url in urls:
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
#print titles only
h1 = soup.find("h1", class_= "class-headline")
print(h1.get_text())
If you are going to prompt user for input for each site then it can be done this way
from bs4 import BeautifulSoup
import requests
import pprint
import re
import pyperclip
urls = ['www.website1.com', 'www.website2.com', 'www.website3.com', .....]
#scrape elements
msg = 'Enter Url, to exit type q and hit enter.'
url = input(msg)
while(url!='q'):
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
#print titles only
h1 = soup.find("h1", class_= "class-headline")
print(h1.get_text())
input(msg)
If you want to scrape links in batches. Specify a batch size and iterate over it.
from bs4 import BeautifulSoup
import requests
import pprint
import re
import pyperclip
batch_size = 5
urllist = ["url1", "url2", "url3", .....]
url_chunks = [urllist[x:x+batch_size] for x in xrange(0, len(urllist), batch_size)]
def scrape_url(url):
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
h1 = soup.find("h1", class_= "class-headline")
return (h1.get_text())
def scrape_batch(url_chunk):
chunk_resp = []
for url in url_chunk:
chunk_resp.append(scrape_url(url))
return chunk_resp
for url_chunk in url_chunks:
print scrape_batch(url_chunk)

Categories

Resources