Created
October 22, 2014 20:59
-
-
Save philrenaud/06e8daeaff8e27f5646f to your computer and use it in GitHub Desktop.
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 urllib2 | |
import json | |
import logging | |
logger = logging.getLogger() | |
logger.setLevel(logging.DEBUG) | |
with open('folks.json', 'r') as f: | |
folks = json.load(f) | |
html = urllib2.urlopen( folks[1] ).read() | |
soup = BeautifulSoup( html ) | |
parsedFolks = [] | |
for folk in folks: | |
logging.debug(folk) | |
html = urllib2.urlopen( folk ).read() | |
soup = BeautifulSoup( html ) | |
parsedPerson = {} | |
if soup.find('li', {'class': 'ProfileNav-item--tweets'}): | |
parsedPerson['num_tweets'] = soup.find('li', {'class': 'ProfileNav-item--tweets'}).find('span', {'class':'ProfileNav-value'}).text | |
if soup.find('li', {'class': 'ProfileNav-item--following'}): | |
parsedPerson['following'] = soup.find('li', {'class': 'ProfileNav-item--following'}).find('span', {'class':'ProfileNav-value'}).text | |
if soup.find('li', {'class': 'ProfileNav-item--followers'}): | |
parsedPerson['followers'] = soup.find('li', {'class': 'ProfileNav-item--followers'}).find('span', {'class':'ProfileNav-value'}).text | |
if soup.find('li', {'class': 'ProfileNav-item--favorites'}): | |
parsedPerson['favorites'] = soup.find('li', {'class': 'ProfileNav-item--favorites'}).find('span', {'class':'ProfileNav-value'}).text | |
if soup.find('a', {'class': 'ProfileHeaderCard-nameLink'}): | |
parsedPerson['name'] = soup.find('a', {'class': 'ProfileHeaderCard-nameLink'}).text | |
if soup.find('a', {'class': 'ProfileHeaderCard-screennameLink'}): | |
parsedPerson['handle'] = soup.find('a', {'class': 'ProfileHeaderCard-screennameLink'}).text.replace('@','') | |
if soup.find('p', {'class': 'ProfileHeaderCard-bio'}): | |
parsedPerson['bio'] = soup.find('p', {'class': 'ProfileHeaderCard-bio'}).text | |
if soup.find('span', {'class': 'ProfileHeaderCard-joinDateText'}): | |
parsedPerson['joinDate'] = soup.find('span', {'class': 'ProfileHeaderCard-joinDateText'})['title'] | |
if soup.find('span', {'class': 'ProfileHeaderCard-locationText'}): | |
parsedPerson['location'] = soup.find('span', {'class': 'ProfileHeaderCard-locationText'}).text | |
if soup.find('span', {'class': 'ProfileHeaderCard-urlText'}).find('a'): | |
parsedPerson['url'] = soup.find('span', {'class': 'ProfileHeaderCard-urlText'}).find('a')['title'] | |
if soup.find('img', {'class': 'ProfileAvatar-image'}): | |
parsedPerson['avatar'] = soup.find('img', {'class': 'ProfileAvatar-image'})['src'].replace('400x400', 'mini') | |
parsedPerson['tweets'] = [] | |
if soup.find_all('div', {'class': 'ProfileTweet'}): | |
for tweet in soup.find_all('div', {'class': 'ProfileTweet'}): | |
if 'is-pinned' not in tweet['class']: | |
theTweet = {} | |
if tweet.find('p', {'class': 'ProfileTweet-text'}): | |
theTweet['text'] = tweet.find('p', {'class': 'ProfileTweet-text'}).text | |
if tweet.find('span', {'class': 'js-short-timestamp'}): | |
if tweet.find('span', {'class': 'js-short-timestamp'}).has_attr('data-time'): | |
theTweet['timestamp'] = tweet.find('span', {'class': 'js-short-timestamp'})['data-time'] | |
if tweet.find('span', {'class': 'ProfileTweet-screenname'}): | |
theTweet['author'] = tweet.find('span', {'class': 'ProfileTweet-screenname'}).text.lstrip().rstrip().replace('@','') | |
parsedPerson['tweets'].append(theTweet) | |
parsedFolks.append(parsedPerson) | |
with open('parsed_folks.json', 'w') as outfile: | |
json.dump(parsedFolks, outfile) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment