def process_site(site):
""" Process the feeds of a site """
logging.info("")
logging.info("* site: %s", site)
logging.info("")
body = _getfeed(site)
if not body:
logging.warning("main_rss: empty feed")
return
each_post = _select_generator(body)
for post in each_post(body):
logging.info("")
logging.info("- [%04d-%02d-%02d] <%s>", post["year"], post["month"],
post["day"], post["link"])
if SETTINGS["before_tuple"]:
if post["year"] > SETTINGS["before_tuple"][0]:
logging.info("main_rss: year greater than %d; skip",
SETTINGS["before_tuple"][0])
continue
if post["month"] > SETTINGS["before_tuple"][1]:
logging.info("main_rss: month greater than %d; skip",
SETTINGS["before_tuple"][1])
continue
if post["day"] >= SETTINGS["before_tuple"][2]:
logging.info(
"main_rss: day greater than (or equal to) %d; "
"skip", SETTINGS["before_tuple"][2])
continue
# Pause a bit before we process each post
time.sleep(random.random() + 0.5)
link = _get_final_url(post["link"])
if not link:
continue
link = _canonicalize(link)
path = _to_bitpath(link)
if not path:
continue
path = subr_misc.make_post_folder(site, path)
logging.info("- <%s> => .../%s", link, path)
logging.info("")
if os.path.isdir(path):
logging.warning("main_rss: dup <.../%s>; skip", path)
continue
success = subr_misc.mkdir_recursive_idempotent(path)
if not success:
continue
path += os.sep
path += "%02d-%02d-%02d.html" % (post["year"], post["month"],
post["day"])
_savepost(link, path)
def process_site(site):
""" Process the feeds of a site """
logging.info("")
logging.info("* site: %s", site)
logging.info("")
body = _getfeed(site)
if not body:
logging.warning("main_rss: empty feed")
return
each_post = _select_generator(body)
for post in each_post(body):
logging.info("")
logging.info("- [%04d-%02d-%02d] <%s>", post["year"], post["month"],
post["day"], post["link"])
if SETTINGS["before_tuple"]:
if post["year"] > SETTINGS["before_tuple"][0]:
logging.info("main_rss: year greater than %d; skip",
SETTINGS["before_tuple"][0])
continue
if post["month"] > SETTINGS["before_tuple"][1]:
logging.info("main_rss: month greater than %d; skip",
SETTINGS["before_tuple"][1])
continue
if post["day"] >= SETTINGS["before_tuple"][2]:
logging.info("main_rss: day greater than (or equal to) %d; "
"skip", SETTINGS["before_tuple"][2])
continue
# Pause a bit before we process each post
time.sleep(random.random() + 0.5)
link = _get_final_url(post["link"])
if not link:
continue
link = _canonicalize(link)
path = _to_bitpath(link)
if not path:
continue
path = subr_misc.make_post_folder(site, path)
logging.info("- <%s> => .../%s", link, path)
logging.info("")
if os.path.isdir(path):
logging.warning("main_rss: dup <.../%s>; skip", path)
continue
success = subr_misc.mkdir_recursive_idempotent(path)
if not success:
continue
path += os.sep
path += "%02d-%02d-%02d.html" % (post["year"], post["month"],
post["day"])
_savepost(link, path)
def process_site(site, noisy):
""" Process the feeds of a site """
logging.info("")
logging.info("* site: %s", site)
logging.info("")
result = subr_rss.fetch(site, noisy=noisy)
if not result or not result[0]:
return
body = result[0]
if "<rss" not in body:
handler = sax_atom.AtomHandler()
else:
handler = sax_rss.RssHandler()
sax.parseString(body, handler)
content = zip(handler.links, handler.pub_dates)
for link, date in content:
if date[0] < 2013:
continue
if date[1] != 5:
continue
if date[2] < 15:
continue
logging.info("")
logging.info("- <%s>", link)
logging.info("")
folder = subr_misc.make_post_folder(date, site)
subr_misc.mkdir_recursive_idempotent(folder)
time.sleep(random.randrange(5, 8))
link = subr_bitly.shorten(link, noisy=noisy)
filename = subr_misc.bitlink_to_filename(link)
pname = os.sep.join([folder, filename])
if os.path.isfile(pname):
logging.info("main: file already exists: %s", pname)
continue
time.sleep(random.randrange(5, 8))
_, body = subr_http.fetch_url(link, noisy=noisy)
filep = open(pname, "w")
filep.write(body)
filep.close()
def process_site(site, noisy):
""" Process the feeds of a site """
logging.info("")
logging.info("* site: %s", site)
logging.info("")
result = subr_rss.fetch(site, noisy=noisy)
if not result or not result[0]:
return
body = result[0]
if "<rss" not in body:
handler = sax_atom.AtomHandler()
else:
handler = sax_rss.RssHandler()
sax.parseString(body, handler)
content = zip(handler.links, handler.pub_dates)
for link, date in content:
if date[0] < 2013:
continue
if date[1] != 5:
continue
if date[2] < 15:
continue
logging.info("")
logging.info("- <%s>", link)
logging.info("")
folder = subr_misc.make_post_folder(date, site)
subr_misc.mkdir_recursive_idempotent(folder)
time.sleep(random.randrange(5, 8))
link = subr_bitly.shorten(link, noisy=noisy)
filename = subr_misc.bitlink_to_filename(link)
pname = os.sep.join([folder, filename])
if os.path.isfile(pname):
logging.info("main: file already exists: %s", pname)
continue
time.sleep(random.randrange(5, 8))
_, body = subr_http.fetch_url(link, noisy=noisy)
filep = open(pname, "w")
filep.write(body)
filep.close()