-
Notifications
You must be signed in to change notification settings - Fork 2
Expand file tree
/
Copy pathasync_url_reader.py
More file actions
executable file
·108 lines (92 loc) · 3.17 KB
/
async_url_reader.py
File metadata and controls
executable file
·108 lines (92 loc) · 3.17 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
#!/usr/bin/env python3
# areq.py
"""Asynchronously get links embedded in multiple pages' HMTL."""
import asyncio
import logging
import re
import sys
from typing import IO
import urllib.error
import urllib.parse
import aiofiles
import aiohttp
from aiohttp import ClientSession
logging.basicConfig(
format="%(asctime)s %(levelname)s:%(name)s: %(message)s",
level=logging.DEBUG,
datefmt="%H:%M:%S",
stream=sys.stderr,
)
logger = logging.getLogger("areq")
logging.getLogger("chardet.charsetprober").disabled = True
HREF_RE = re.compile(r'href="(.*?)"')
async def fetch_html(url: str, session: ClientSession, **kwargs) -> str:
"""GET request wrapper to fetch page HTML.
kwargs are passed to `session.request()`.
"""
resp = await session.request(method="GET", url=url, **kwargs)
resp.raise_for_status()
logger.info("Got response [%s] for URL: %s", resp.status, url)
html = await resp.text()
return html
async def parse(url: str, session: ClientSession, **kwargs) -> set:
"""Find HREFs in the HTML of `url`."""
found = set()
try:
html = await fetch_html(url=url, session=session, **kwargs)
except (
aiohttp.ClientError,
aiohttp.http_exceptions.HttpProcessingError,
) as e:
logger.error(
"aiohttp exception for %s [%s]: %s",
url,
getattr(e, "status", None),
getattr(e, "message", None),
)
return found
except Exception as e:
logger.exception(
"Non-aiohttp exception occured: %s", getattr(e, "__dict__", {})
)
return found
else:
for link in HREF_RE.findall(html):
try:
abslink = urllib.parse.urljoin(url, link)
except (urllib.error.URLError, ValueError):
logger.exception("Error parsing URL: %s", link)
pass
else:
found.add(abslink)
logger.info("Found %d links for %s", len(found), url)
return found
async def write_one(file: IO, url: str, **kwargs) -> None:
"""Write the found HREFs from `url` to `file`."""
res = await parse(url=url, **kwargs)
if not res:
return None
async with aiofiles.open(file, "a") as f:
for p in res:
await f.write(f"{url}\t{p}\n")
logger.info("Wrote results for source URL: %s", url)
async def bulk_crawl_and_write(file: IO, urls: set, **kwargs) -> None:
"""Crawl & write concurrently to `file` for multiple `urls`."""
async with ClientSession() as session:
tasks = []
for url in urls:
tasks.append(
write_one(file=file, url=url, session=session, **kwargs)
)
await asyncio.gather(*tasks)
if __name__ == "__main__":
import pathlib
import sys
assert sys.version_info >= (3, 7), "Script requires Python 3.7+."
here = pathlib.Path(__file__).parent
with open(here.joinpath("urls.txt")) as infile:
urls = set(map(str.strip, infile))
outpath = here.joinpath("foundurls.txt")
with open(outpath, "w") as outfile:
outfile.write("source_url\tparsed_url\n")
asyncio.run(bulk_crawl_and_write(file=outpath, urls=urls))