Last active
August 29, 2015 14:03
-
-
Save CloudCray/d93d3d72ff51157a87df to your computer and use it in GitHub Desktop.
Comp Manager Entry List Scraper - Single Event
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
# Python 3.4 | |
import urllib.request as r | |
import urllib.parse as p | |
import gzip | |
import io | |
import bs4 | |
import os | |
import csv | |
url = "http://www.compmngr.com/michcomp15/MichComp15_EntryLists.htm" | |
def get_page_text(url, referer=None, header=[], data=None): | |
req = r.Request(url) | |
for k in HEADERS.keys(): | |
req.add_header(k, HEADERS[k]) | |
for h in COOKIES: | |
req.add_header(h[0], h[1]) | |
for h in header: | |
req.add_header(h[0], h[1]) | |
if referer: | |
req.add_header("Referer", referer) | |
if data: | |
resp = r.urlopen(req, data) | |
else: | |
resp = r.urlopen(req) | |
if resp.getheader("Set-Cookie"): | |
COOKIES.append(("Cookie", resp.getheader("Set-Cookie"))) | |
enc = resp.headers.get("Content-Encoding") | |
output = None | |
if enc: | |
if enc.upper() == "GZIP": | |
bi = io.BytesIO(resp.read()) | |
gf = gzip.GzipFile(fileobj=bi, mode="rb") | |
output = gf.read() | |
else: | |
output = resp.read() | |
else: | |
output = resp.read() | |
if type(output) is bytes: | |
output = output.decode("ascii", "replace") | |
return output | |
HEADERS = { | |
"Host": "www.compmngr.com", | |
"Connection": "keep-alive", | |
"Accept": r"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8", | |
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36", | |
"Accept-Encoding": "gzip,deflate,sdch", | |
"Accept-Language": "en-US,en;q=0.8"} | |
COOKIES = [] | |
page_text = get_page_text(url) | |
page_soup = bs4.BeautifulSoup(page_text) | |
divs = page_soup.findChildren("div") | |
div_tables = [x for x in divs if "TABLE" in x["id"]] | |
events = [] | |
for div in div_tables: | |
table = div.find("table") | |
if table: | |
for item in table.findAll("td"): | |
text = item.text | |
if not text == "Event" and text not in events: | |
events.append(text) | |
entries = {x: [] for x in events} | |
for event in events: | |
entrants = [y for y in divs if event in y.text] | |
for x in entrants: | |
persons = x.findChildren("strong") | |
person_1 = persons[0].text.replace("Entries for ", "") | |
person_2 = persons[1].text.replace("With ","") | |
entries[event].append((person_1, person_2)) | |
output_as_list = [] | |
for k in entries: | |
for couple in entries[k]: | |
out_rec = [k, couple[0], couple[1]] | |
output_as_list.append(out_rec) | |
filename = url.split("/")[-1].replace(".", "_") + ".csv" | |
out_file = open(filename, "w", newline="\n") | |
writer = csv.writer(out_file) | |
writer.writerow(["Event", "Lead", "Follow"]) | |
for row in output_as_list: | |
writer.writerow(row) | |
out_file.close() |
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
# Python 3.4 | |
import urllib.request as r | |
import urllib.parse as p | |
import gzip | |
import io | |
import bs4 | |
import os | |
entrants = [x for x in divs if "AC- Adult (19+) Amateur International Ballroom Championships (W/T/VW/F/Q)" in x.text] | |
url = r"http://www.compmngr.com/manhattan2014/Manhattan2014_HeatLists.htm" | |
def get_page_text(url, referer=None, header=[], data=None): | |
req = r.Request(url) | |
for k in HEADERS.keys(): | |
req.add_header(k, HEADERS[k]) | |
for h in COOKIES: | |
req.add_header(h[0], h[1]) | |
for h in header: | |
req.add_header(h[0], h[1]) | |
if referer: | |
req.add_header("Referer", referer) | |
if data: | |
resp = r.urlopen(req, data) | |
else: | |
resp = r.urlopen(req) | |
if resp.getheader("Set-Cookie"): | |
COOKIES.append(("Cookie", resp.getheader("Set-Cookie"))) | |
enc = resp.headers.get("Content-Encoding") | |
output = None | |
if enc: | |
if enc.upper() == "GZIP": | |
bi = io.BytesIO(resp.read()) | |
gf = gzip.GzipFile(fileobj=bi, mode="rb") | |
output = gf.read() | |
else: | |
output = resp.read() | |
else: | |
output = resp.read() | |
if type(output) is bytes: | |
output = output.decode("ascii", "replace") | |
return output | |
HEADERS = { | |
"Host": "www.compmngr.com", | |
"Connection": "keep-alive", | |
"Accept": r"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8", | |
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36", | |
"Accept-Encoding": "gzip,deflate,sdch", | |
"Accept-Language": "en-US,en;q=0.8"} | |
COOKIES = [] | |
page_text = get_page_text(url) | |
page_soup = bs4.BeautifulSoup(page_text) | |
divs = page_soup.findChildren("div") | |
competitors = {} | |
for x in entrants: | |
persons = x.findChildren("strong") | |
person_1 = persons[0].text.replace("Entries for ", "") | |
person_2 = persons[1].text.replace("With ","") | |
if competitors.get(person_2) is None: | |
competitors[person_1] = person_2 | |
for x in competitors: | |
print(x + " and " + competitors[x]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment