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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
|
#!/bin/python
#some useful web-related scripts, such as crawling, searching for, downloading certain data
import os
import requests
from bs4 import BeautifulSoup
import re
import sys
import time
from urllib.parse import urlsplit, urljoin
from util import *
#returns an array of img src urls from a 4chan thread
def pull4chImgs(url):
result = []
resp = requests.get(url)
html = BeautifulSoup(resp.text, 'html.parser')
for a in html.find_all('a'):
if 'class' in a.attrs and 'fileThumb' in a.attrs['class']:
url = a.get('href')
if url[0:2] == '//':
url = 'https:' + url
result.append(url)
return result
def pullVids(url):
result = []
resp = requests.get(url)
html = BeautifulSoup(resp.text, 'html.parser')
for a in html.find_all('a'):
if '.webm' in a.get('href'):
result.append(a.get('href'))
return result
def pullImgs(url):
result = []
resp = requests.get(url)
html = BeautifulSoup(resp.text, 'html.parser')
for img in html.find_all('img'):
srcURL = img.get('src')
result.append(srcURL)
return result
#i used this for downloading a bunch of pdfs from some prepper website
def pullPDFs(url, depth=0, alreadycrawled=None, max_depth=5, delay=5.0, timeout=20.0, user_agent=None):
"""Return a list of discovered PDF URLs by crawling from `url`.
Notes:
- Avoids mutable default args.
- `max_depth` and `delay` make it safer to run from a CLI.
"""
if alreadycrawled is None:
alreadycrawled = []
if depth > max_depth or url == '' or url is None or url in alreadycrawled:
return []
baseurl = url[0:url.find('/', 8) + 1]
result = []
print(url)
headers = {}
if user_agent:
headers["User-Agent"] = user_agent
resp = requests.get(url, headers=headers, timeout=timeout)
html = BeautifulSoup(resp.text, 'html.parser')
alreadycrawled.append(url)
for a in html.find_all('a'):
url = a.get('href')
if url is None or url == '' or url == '/':
continue
if baseurl not in url and 'http' in url[0:4]: # external
continue
print('found ' + url)
if 'http' not in url:
url = baseurl + url
if url.find('.pdf') > 0 and os.path.isfile(url):
result.append(url)
else:
time.sleep(delay)
result = result + pullPDFs(
url,
depth + 1,
alreadycrawled,
max_depth=max_depth,
delay=delay,
timeout=timeout,
user_agent=user_agent,
)
return result
#return a list of strings of all the links on the given webpage (<a> elements) whose href contains the given search string
def getLinksContainingStr(url, s):
result = []
resp = requests.get(url)
html = BeautifulSoup(resp.text, 'html.parser')
for link in html.find_all('a'):
if link == None:
print('non')
continue
h = link.get('href')
if h and s in h:
result.append(url + '/' + h)
return result
def downloadFromBandcamp(url, path):
res = getAnchorWithPattern(url, ['track/','album/'])
log(f'found {len(res)} tracks/albums for {str(url)}')
if len(res) > 0:
for page in res:
print()
cmd(f'yt-dlp -x --audio-format flac --audio-quality 0 -P {path} {str(page)}')
def downloadFromYoutubeMusic(url, path):
res = getAnchorWithPattern(url, ['browse/.*_.+'])
log(f'found {len(res)} tracks for {str(url)}')
if len(res) > 0:
for page in res:
cmd(f'ytdla -P {path} {str(page)}')
#write each element of list l to file of path p
def writeListToFile(l, path, append=False):
f = open(path, 'a' if append else 'w')
for e in l:
f.write(str(e))
f.write('\n')
f.close()
def getAnchorWithPattern(url, pattern, content=None):
result = []
patterns = pattern if isinstance(pattern, (list, tuple, set)) else [pattern]
if content is None:
resp = requests.get(url)
html = BeautifulSoup(resp.text, 'html.parser')
else:
html = BeautifulSoup(content, 'html.parser')
parts = urlsplit(url)
base_url = f'{parts.scheme}://{parts.netloc}/'
for link in html.find_all('a'):
if link == None:
print('non')
continue
h = link.get('href')
if h and any(re.search(single_pattern, h) for single_pattern in patterns):
if h[0:4] != 'http':
h = urljoin(base_url, h.lstrip('/'))
result.append(h)
else:
print(h)
return result
def writeListToFile(l, path, append=False):
f = open(path, 'a' if append else 'w')
for e in l:
f.write(str(e))
f.write('\n')
f.close()
def ytdlaFromFile(path):
'''downloads audio from each url in the file at path'''
with open(path, 'r') as f:
for line in f:
url = line.strip()
if url != '':
cmd('echo ' + url)
#if len(sys.argv) < 2:
# sys.exit(0)
#for url in pull4chImgs(sys.argv[1]):
# print(url)
|
