Skip to content

add new feature #2

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

Open
neofit77 wants to merge 4 commits into
base: master
Choose a base branch
from
Open

add new feature #2

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1698446
add a feature to the scraper that it can scrap the email
neofit77 Apr 23, 2020
aa28d78
Update restaurants_scraper.py
neofit77 Apr 23, 2020
f2bdc56
Update restaurants_scraper.py
neofit77 Apr 23, 2020
1ab4592
email update
neofit77 Apr 24, 2020
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
11 changes: 9 additions & 2 deletions restaurants_scraper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
from bs4 import BeautifulSoup
from datetime import datetime
from multiprocessing.pool import ThreadPool
import re

logging.basicConfig(level=logging.INFO)

Expand Down Expand Up @@ -40,7 +41,7 @@ def _get_last_page_offset(url_html):
return int(last_page_offset)


def _restaurant_info(restaurant_data):
def _restaurant_info(restaurant_data, email):
restaurant_dict = {
"name": restaurant_data.get("name"),
"priceRange": restaurant_data.get("priceRange"),
Expand All @@ -49,6 +50,7 @@ def _restaurant_info(restaurant_data):
"address": restaurant_data.get("address").get("streetAddress"),
"locality": restaurant_data.get("address").get("addressLocality"),
"url": BASE_URL + restaurant_data.get("url"),
'email': email
}
return restaurant_dict

Expand Down Expand Up @@ -91,7 +93,12 @@ def get_restaurant_info(restaurant_tag):
restaurant_html = get_html_and_parse(restaurant_url)
restaurant_data = restaurant_html.findAll("script")[1].contents[0]
restaurant_data = ast.literal_eval(restaurant_data)
restaurant_information = _restaurant_info(restaurant_data)
try:
mailA = restaurant_html.findAll('a', href=re.compile("mailto"))
em = mailA[0]['href'].split('?')[0][7:]
except:
em = ''
restaurant_information = _restaurant_info(restaurant_data, em)
if restaurant_information:
restaurants_list.append(restaurant_information)
else:
Expand Down