How to fix ''bytes' object has no attribute 'findAll'' - object

Question

I am trying to import videoId from a pickle folder and then print the description of the youtube video.and i am getting this error ='bytes' object has no attribute 'findAll'i want to extract the description with videoid and title in csv
cwd=os.getcwd()
parent_folder=os.path.join(cwd,'Data') pickle_out=open("C:/Users/india/Desktop/PARUL/Data/Pickle/vid_ids_dict.pickle","rb")
vid_id_dict=pickle.load(pickle_out)
dataset_folder=os.path.join(parent_folder,"Dataset")
if not os.path.exists(dataset_folder):
os.makedirs(dataset_folder)
csv_file_path= os.path.join(parent_folder,'main.csv')
base = "https://www.youtube.com/watch?v="
for keys, values in vid_id_dict.items():
for key in keys:
query_dataset_folder=os.path.join(dataset_folder,key)
if not os.path.exists(query_dataset_folder):
os.makedirs(query_dataset_folder)
for VidID in values:
r = requests.get(base+VidID)
soup = bs(r.text,'html.parser').encode("utf-8")
name=VidID+".txt"
save_description_link=os.path.join(query_dataset_folder,name)
f= open(save_description_link,"a+")
for title in soup.findAll('p', attrs={'id': 'eow-description'}):
description=title.text.strip()
f.write(description)
print(description)
f.close()
for title in soup.findAll('span', attrs={'class': 'watch-title'}):
vid_title= title.text.strip()
print(vid_title)
with open(csv_file_path, 'a+') as csvfile:
fieldnames = ['Video id', 'Title','Description','Category']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({'Video id': VidID, 'Title': vid_title, 'Description':description,'Category':key})
ERROR-
AttributeError Traceback (most recent call last)
in
35 f= open(save_description_link,"a+")
36
---> 37 for title in soup.findAll('p', attrs={'id': 'eow-
description'}):
38 description=title.text.strip()
39 f.write(description)
AttributeError: 'bytes' object has no attribute 'findAll'

Answer 1

I'm assume that you're using requests module for getting the http responses.
Just replace your code with:
r.encoding = 'utf-8'
soup = bs(req.content, 'html.parser')
Final Running code:
for keys, values in vid_id_dict.items():
for key in keys:
query_dataset_folder=os.path.join(dataset_folder,key)
if not os.path.exists(query_dataset_folder):
os.makedirs(query_dataset_folder)
for VidID in values:
r = requests.get(base+VidID)
r.encoding = 'utf-8'
soup = bs(r.content, 'html.parser')
name=VidID+".txt"
save_description_link=os.path.join(query_dataset_folder,name)
f= open(save_description_link,"a+")
for title in soup.findAll('p', attrs={'id': 'eow-description'}):
description=title.text.strip()
f.write(description)
print(description)
f.close()
for title in soup.findAll('span', attrs={'class': 'watch-title'}):
vid_title= title.text.strip()
print(vid_title)
with open(csv_file_path, 'a+') as csvfile:
fieldnames = ['Video id', 'Title','Description','Category']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({'Video id': VidID, 'Title': vid_title, 'Description':description,'Category':key})