Created
April 4, 2018 18:19
-
-
Save QuantumCalzone/76efbb6d227ff7f794e19b397726c015 to your computer and use it in GitHub Desktop.
Scrapes a user's public Yelp bookmarks and exports them to a CSV
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#requires beautifulsoup4 | |
#run 'pip install bs4' without quotes in command prompt first for wondows or 'pip3 install bs4' for mac | |
import bs4 | |
import re | |
pattern = re.compile(r"(?<=\>)(.*?)(?=\<)") | |
debug = "Done!" | |
from urllib.request import urlopen as uReq | |
from bs4 import BeautifulSoup as soup | |
print("\n") | |
userName = input("Enter is the name of the person who owns this Yelp profile: ") | |
#create the initial csv file | |
filename = userName+"sYelpBookmarks.csv" | |
#f is the normal convention for a File Writer | w stands for "Write" | |
f = open(filename, "w") | |
headers = "BizName,Rating,Reviews,Catagories,City\n" | |
f.write(headers) | |
pageIndex = 0 | |
print("\n") | |
urlSource = input("Paste thir Yelp bookmark URL: ") | |
print("\n") | |
pageAmount = int(input("Enter the amount of pages they have: ")) | |
maxPages = (pageAmount * 50) + 1 | |
print("\n") | |
print("Downloading...") | |
while pageIndex < maxPages: | |
myUrl = urlSource+"&start="+str(pageIndex) | |
#opening up connection | |
uClient = uReq(myUrl) | |
#grabbing the page | |
page_html = uClient.read() | |
uClient.close() | |
#html parsing | |
page_soup = soup(page_html, "html.parser") | |
#grabs each product | |
containers = page_soup.findAll("li", {"class":"js-bookmark-row"}) | |
for container in containers: | |
containerBizName = container.findAll("a", {"class":"biz-name js-analytics-click"}) | |
bizName = containerBizName[0].span.contents[0] | |
containerBizRating = container.findAll("div", {"class":"biz-rating biz-rating-large clearfix"}) | |
rating = containerBizRating[0].div["title"] | |
rating = rating.replace(" star rating", "") | |
reviews = containerBizRating[0].span.contents[0].strip() | |
reviews = reviews.replace(" reviews", "") | |
reviews = reviews.replace(" review", "") | |
containerCatagories = container.findAll("span", {"class":"category-str-list"}) | |
catagories = "" | |
rawCatagories = str(containerCatagories[0]) | |
matches = pattern.finditer(rawCatagories) | |
for match in matches: | |
if (len(catagories) > 0): catagories += "|" | |
try: | |
newCatagory = match.group() | |
newCatagory = newCatagory.replace("&", "and") | |
newCatagory = newCatagory.replace(",", "|") | |
catagories += newCatagory | |
except: | |
catagories = str(match) | |
pass | |
containerCity = container.findAll("small", {"class":"biz-city"}) | |
city = containerCity[0].contents[0] | |
print("bizName: "+bizName) | |
print("rating: "+rating) | |
print("reviews: "+reviews) | |
print("catagories: "+catagories) | |
print("city: "+city) | |
print("\n") | |
f.write( | |
bizName.replace(",", "|") + "," + | |
rating + "," + | |
reviews + "," + | |
catagories.replace(",", "|") + "," + | |
city.replace(",", "|") + "," + | |
"\n" | |
) | |
pageIndex += 50 | |
f.close() | |
print(debug) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment