GPS Scraper

scrape.py

from io import BytesIO

from bs4 import BeautifulSoup
import exifread
import requests

# the url to rip from... you could easily use .format to replace 1
# with any page you like, or even loop through many pages
url = 'http://tinypic.com/images.php?page=1'

# retrieve the URL
summary_req = requests.get(url)

# parse the text of the request into HTML
summary_html = BeautifulSoup(summary_req.text, 'html.parser')
# find the <div class="browse">...</div>
browse_div = summary_html.find('div', class_='browse')
# find all the <a href> tags inside the browse div
browse_links = browse_div.find_all('a')

# loop over the browse links
for link in browse_links:
    # the URL for the individual image page
    image_page = link['href']
    # retrieve the image page
    image_page_req = requests.get(image_page)
    # parse the image page HTML
    image_page_html = BeautifulSoup(image_page_req.text, 'html.parser')
    # find the <div id="imgFrame">...</div>
    img_frame_div = image_page_html.find('div', id='imgFrame')
    # find the first <a href> inside the imgFrame div and get the value of href
    img_frame_link = img_frame_div.find('a')['href']

    # request the actual image (jpg)
    image_req = requests.get(img_frame_link)
    # convert the response into an in memory file-like object
    image_file = BytesIO(image_req.content)
    # look for EXIF information
    tags = exifread.process_file(image_file)

    # print the link to the image
    print(img_frame_link)
    # print the GPS info - we use tags.get('blah') as opposed to
    # tags['blah'] because if 'blah' doesn't exist, get returns None
    # instead of giving us an error
    print('Long: {}'.format(tags.get('GPS GPSLongitude')))
    print('Long Ref: {}'.format(tags.get('GPS GPSLongitudeRef')))
    print('Lat: {}'.format(tags.get('GPS GPSLatitude')))
    print('Lat Ref: {}'.format(tags.get('GPS GPSLatitudeRef')))
    # print a blank line before the next entry
    print()