Last active
August 29, 2015 14:00
-
-
Save achavez/11300485 to your computer and use it in GitHub Desktop.
Scraper for schiefferschool.tcu.edu
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
from bs4 import BeautifulSoup | |
import requests, csv | |
# Settings | |
base_url = 'http://www.schiefferschool.tcu.edu/' | |
story_list_url = 'more_headlines.asp' | |
blacklist = ['931.htm', '1021.asp'] | |
# Get a list of articles to scrape from the More Headlines page | |
news_page = requests.get(base_url + story_list_url) | |
if news_page.status_code == 200: | |
encoding = news_page.encoding | |
story_list = BeautifulSoup(news_page.text, from_encoding=encoding) | |
story_list = story_list.find("div", id="GeneralContent") | |
print "Downloaded story list from " + base_url + story_list_url | |
else: | |
error_message = str(news_page.status_code) + ' error downloading story list' | |
raise Exception(error_message) | |
# Loop over the list of URLs from the story page and save them in a CSV | |
with open('output.csv', 'wb') as outputfile: | |
csvwriter = csv.writer(outputfile) | |
counter = 0 | |
for link in story_list.find_all('a'): | |
if link.get('href') in blacklist: | |
continue | |
url = 'http://www.schiefferschool.tcu.edu/' + link.get('href') | |
print("Extracting text from " + url) | |
story = requests.get(url) | |
encoding = story.encoding | |
if story.status_code == 200: | |
# Parse the story page | |
story = BeautifulSoup(story.text, from_encoding=encoding) | |
headline = story.find("h3", class_="hugePurpleHeadline").string.encode('ascii', 'xmlcharrefreplace') | |
body = story.find("span", class_="news_body_content").encode('ascii') | |
body = body[33:len(body)-48].strip() # Strip out wrapper tag | |
# Extract date and dateline from story meta | |
for span in story.find_all("span", class_="news_bodybold"): | |
if span.parent.name == 'br': | |
span = span.get_text().strip().split("\n") | |
dateline = span[0] | |
date = span[len(span) - 1] | |
# Get the image and caption | |
img = story.select('#GeneralContent table[align="right"] img') | |
if img: | |
img = img[0]['src'] | |
# Download the image | |
img_url = base_url + img | |
print "Downloading image " + img_url | |
r = requests.get(img_url, stream=True) | |
img_file = img[7:] | |
with open(img_file, 'wb') as fd: | |
for chunk in r.iter_content(65536): | |
fd.write(chunk) | |
else: | |
img_file = '' | |
# Write the text to a CSV | |
csvwriter.writerow([url, headline, body, date, dateline, img_file]) | |
# Iterate the counter | |
counter = counter + 1 | |
else: | |
error_message = str(story.status_code) + ' error downloading story' | |
raise Exception(error_message) | |
print "Extracted " + str(counter) + " stories from " + story_list_url |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment