Created
March 28, 2015 20:28
-
-
Save dmil/a76ea4087d71d3e12f03 to your computer and use it in GitHub Desktop.
Scrape PDFS
This file contains 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
""" | |
Stub for scraping-related jobs | |
CSS Selectors Reference: http://www.w3schools.com/cssref/css_selectors.asp | |
""" | |
import requests, lxml.html | |
import re | |
# Select the element using a CSS Selector | |
def get_url_from_element(element): | |
pattern = r'<a href="\/url\?q=(http.*\.pdf)' | |
m = re.search(pattern, lxml.html.tostring(element)) | |
if m: | |
return m.group(1) | |
else: | |
return "" | |
def scrape_page(page_no): | |
url = "https://www.google.com/search?q=site%3Ahouse.gov+ttf++pdf&biw=1366&bih=623&source=lnt&tbs=cdr%3A1%2Ccd_min%3A1%2F1%2F2015%2Ccd_max%3A&tbm=#q=site:house.gov+%22Truth+in+Testimony%22+pdf&tbs=cdr:1,cd_min:1/1/2015&start=" + str(page_no * 10) | |
response = requests.get(url) | |
doc = lxml.html.fromstring(response.content) | |
h3_elements = doc.cssselect("h3") | |
for element in h3_elements: | |
print get_url_from_element(element) | |
print "" | |
for pg in range(0,20): | |
scrape_page(pg) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment