Created
May 11, 2012 13:41
-
-
Save tominsam/2659718 to your computer and use it in GitHub Desktop.
crappy oyster data scraper
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
#!/usr/bin/env python | |
import mechanize | |
import datetime | |
import urllib | |
from bs4 import BeautifulSoup | |
############## | |
username = "fill me in" | |
password = "fill me in" | |
############## | |
start = "https://oyster.tfl.gov.uk/oyster/entry.do" | |
br = mechanize.Browser() | |
br.set_handle_robots(False) # bah | |
# br.set_debug_redirects(True) | |
# br.set_debug_responses(True) | |
# br.set_debug_http(True) | |
br.open(start) | |
br.select_form(name="sign-in") | |
br["j_username"] = username | |
br["j_password"] = password | |
r = br.submit() | |
assert br.viewing_html() | |
postData = urllib.urlencode({ | |
"dateRange": "custom date range", | |
"offset": "0", | |
"rows": "100", | |
"customDateRangeSel": "false", | |
"isJSEnabledForPagenation": "false", | |
"isJSEnabledForPagination": "false", | |
"csDateFrom": (datetime.datetime.utcnow() - datetime.timedelta(days=30)).strftime("%d/%m/%Y"), | |
"csDateTo": datetime.datetime.utcnow().strftime("%d/%m/%Y"), | |
}) | |
r = br.open("https://oyster.tfl.gov.uk/oyster/journeyHistory.do", postData) | |
soup = BeautifulSoup(r.read()) | |
journeyhistory = soup.find("table", {"class": "journeyhistory"}) | |
day = "" | |
for row in journeyhistory.children: | |
if isinstance(row, basestring): | |
continue | |
td_day = row.find("td", {"class": "day-date status-1"}) | |
if td_day: | |
if td_day.find("a"): | |
day = td_day.find("a").get_text().strip() | |
else: | |
day = td_day.get_text().strip() | |
print "===" | |
print day | |
for table in row.find_all("table", {"class": "revealed-table"}): | |
for data_row in table.find_all("tr"): | |
datas = data_row.find_all("td") | |
time = datas[0].get_text().strip() | |
event = datas[1].get_text().strip() | |
print " - %s %s"%(time, event) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment