Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added Cookies + Fixed issues with rating and number of reviews #9

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Added Cookies + Fixed issues with rating and number of reviews #9

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 29 additions & 13 deletions app.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,8 @@
app = Flask(__name__)
extractor = selectorlib.Extractor.from_yaml_file('selectors.yml')

def scrape(url):

def scrape(url):
headers = {
'authority': 'www.amazon.com',
'pragma': 'no-cache',
Expand All @@ -20,18 +21,30 @@ def scrape(url):
'accept-language': 'en-GB,en-US;q=0.9,en;q=0.8',
}

# Using you own data here. Check the cookies from the inspect tab.
cookies = {
"lc-acbin": "en_IN",
"i18n-prefs": "INR",
"session-id": "YOUR_SESSION_ID",
"session-id-time": "YOUR_SESSION_ID_TIME",
"session-token": "YOUR_SESSION_TOKEN",
"ubid-acbin": "YOUR_UBID"}

# Download the page using requests
print("Downloading %s"%url)
r = requests.get(url, headers=headers)
print("Downloading %s" % url)
r = requests.get(url, headers=headers, cookies=cookies)
# Simple check to check if page was blocked (Usually 503)
if r.status_code > 500:
if "To discuss automated access to Amazon data please contact" in r.text:
print("Page %s was blocked by Amazon. Please try using better proxies\n"%url)
print(
"Page %s was blocked by Amazon. Please try using better proxies\n" % url)
else:
print("Page %s must have been blocked by Amazon as the status code was %d"%(url,r.status_code))
print("Page %s must have been blocked by Amazon as the status code was %d" % (
url, r.status_code))
return None
# Pass the HTML of the page and create
data = extractor.extract(r.text,base_url=url)

# Pass the HTML of the page and create
data = extractor.extract(r.text, base_url=url)
reviews = []
for r in data['reviews']:
r["product"] = data["product_title"]
Expand All @@ -41,7 +54,8 @@ def scrape(url):
r['verified_purchase'] = True
else:
r['verified_purchase'] = False
r['rating'] = r['rating'].split(' out of')[0]
if r['rating']:
r['rating'] = r['rating'].split(' out of')[0]
date_posted = r['date'].split('on ')[-1]
if r['images']:
r['images'] = "\n".join(r['images'])
Expand All @@ -53,13 +67,15 @@ def scrape(url):
data['histogram'] = histogram
data['average_rating'] = float(data['average_rating'].split(' out')[0])
data['reviews'] = reviews
data['number_of_reviews'] = int(data['number_of_reviews'].split(' customer')[0])
return data

data['number_of_reviews'] = int(
data['number_of_reviews'].split(' global rating')[0].replace(',', ''))
return data


@app.route('/')
def api():
url = request.args.get('url',None)
url = request.args.get('url', None)
if url:
data = scrape(url)
return jsonify(data)
return jsonify({'error':'URL to scrape is not provided'}),400
return jsonify({'error': 'URL to scrape is not provided'}), 400