alpcentaur/fdb-spider
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

added new database ted.europe.eu, created new case of slow downloading, intergrated scrolling into entrylistpagesdownload

Browse source
This commit is contained in:
alpcentaur 2024-02-09 18:38:49 +00:00
parent 094f092291
commit a0dd469f25
4 changed files with 109 additions and 36 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
main.py
View file

@ -5,8 +5,8 @@ import sys
config = "spiders/config.yaml" config = "spiders/config.yaml"
#list_of_fdbs = eval(sys.argv[1]) #list_of_fdbs = eval(sys.argv[1])
list_of_fdbs = ["giz","evergabe-online","foerderinfo.bund.de-bekanntmachungen"] #list_of_fdbs = ["giz","evergabe-online","foerderinfo.bund.de-bekanntmachungen"]
#list_of_fdbs = ["giz"] list_of_fdbs = ["ted.europa.eu"]
# doing the crawling of government websites # doing the crawling of government websites

BIN
spiders/__pycache__/fdb_spider.cpython-311.pyc
View file

Binary file not shown.

37
spiders/config.yaml
View file

File diff suppressed because one or more lines are too long

104
spiders/fdb_spider.py
View file

@ -146,7 +146,7 @@ class fdb_spider(object):
else: else:
from selenium import webdriver from selenium import webdriver
from selenium.webdriver.chrome.service import Service from selenium.webdriver.chrome.service import Service
#from selenium.webdriver.common.action_chains import ActionChains
from pyvirtualdisplay import Display from pyvirtualdisplay import Display
display = Display(visible=0, size=(800, 800)) display = Display(visible=0, size=(800, 800))
display.start() display.start()
@ -164,6 +164,7 @@ class fdb_spider(object):
service = Service(executable_path='/usr/bin/chromedriver') service = Service(executable_path='/usr/bin/chromedriver')
driver = webdriver.Chrome(options=options, service=service) driver = webdriver.Chrome(options=options, service=service)
# driver = webdriver.Chrome() # driver = webdriver.Chrome()
driver.implicitly_wait(10)
driver.get(entry_jsdomain) driver.get(entry_jsdomain)
for i in range(len(entry_jsiteration_var_list)): for i in range(len(entry_jsiteration_var_list)):
time.sleep(2) time.sleep(2)
@ -176,8 +177,14 @@ class fdb_spider(object):
+ entry_list_jslink2 + entry_list_jslink2
) )
print(entry_iteration_var_list[i]) print(entry_iteration_var_list[i])
time.sleep(2) time.sleep(1)
print('scrolling..')
# scroll into view, because otherwise with javascript generated elements
# it can be that clicking returns an error
driver.execute_script("arguments[0].scrollIntoView();", element)
print('clicking..') print('clicking..')
time.sleep(1)
element.click() element.click()
time.sleep(2) time.sleep(2)
#window_after = driver.window_handles[1] #window_after = driver.window_handles[1]
@ -476,6 +483,7 @@ class fdb_spider(object):
options.add_argument('--disable-dev-shm-usage') options.add_argument('--disable-dev-shm-usage')
service = Service(executable_path='/usr/bin/chromedriver') service = Service(executable_path='/usr/bin/chromedriver')
driver = webdriver.Chrome(options=options, service=service) driver = webdriver.Chrome(options=options, service=service)
driver.implicitly_wait(10)
#driver = webdriver.Chrome() #driver = webdriver.Chrome()
for fdb in list_of_fdbs: for fdb in list_of_fdbs:
print('spidering ' + fdb + ' ..') print('spidering ' + fdb + ' ..')
@ -503,11 +511,21 @@ class fdb_spider(object):
try: try:
fdb_conf_entry_list_javascript_link = fdb_conf_entry_list.get("javascript-link") fdb_conf_entry_list_javascript_link = fdb_conf_entry_list.get("javascript-link")
except Exception as e: except Exception as e:
fdb_conf_entry_list_javascript_link = 'NONE'
print('the javascript link in the config is missing, original error message is:', e) print('the javascript link in the config is missing, original error message is:', e)
try:
fdb_conf_entry_list_slow_downloading = fdb_conf_entry_list.get("slow-downloading")
except Exception as e:
print('the slow-downloading parameter is not set, original error message is:', e)
fdb_conf_entry_list_link1 = fdb_conf_entry_list.get("link1") fdb_conf_entry_list_link1 = fdb_conf_entry_list.get("link1")
fdb_conf_entry_list_link2 = fdb_conf_entry_list.get("link2") fdb_conf_entry_list_link2 = fdb_conf_entry_list.get("link2")
driver.get(fdb_conf_entry_list_link1 + str(i) + fdb_conf_entry_list_link2) if fdb_conf_entry_list_slow_downloading == 'FALSE':
driver.get(fdb_conf_entry_list_link1 + str(i) + fdb_conf_entry_list_link2)
else:
pass
for entry_id in dictionary_entry_list: for entry_id in dictionary_entry_list:
print(entry_id) print(entry_id)
@ -516,7 +534,7 @@ class fdb_spider(object):
# download the html page of the entry # download the html page of the entry
print(entry_link) print(entry_link)
if 'javascript' in entry_link: if 'javascript' in entry_link or fdb_conf_entry_list_javascript_link != 'NONE':
print('oioioi',fdb_conf_entry_list_parent, entry_id, fdb_conf_entry_list_javascript_link) print('oioioi',fdb_conf_entry_list_parent, entry_id, fdb_conf_entry_list_javascript_link)
element = driver.find_element( element = driver.find_element(
"xpath", "xpath",
@ -556,42 +574,58 @@ class fdb_spider(object):
driver.switch_to.window(window_before) driver.switch_to.window(window_before)
if 'javascript' not in entry_link and '.pdf' not in entry_link: if 'javascript' not in entry_link and '.pdf' not in entry_link and fdb_conf_entry_list_javascript_link == 'NONE':
print('blabuuuuuba') print('blabuuuuuba')
#print('oi') #print('oi')
try:
# defining cookie to not end up in endless loop because of cookie banners pointing to redirects
url = entry_link
req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0', 'Cookie':'myCookie=oioioioi'})
response = urllib.request.urlopen(req)
print('response from first one', response)
except Exception as e:
print('cookie giving then downloading did not work, original error is:', e)
try:
response = urllib.request.urlopen(entry_link.encode('ascii', errors='xmlcharrefreplace').decode('ascii'))
print(
"opening the link did not work, try to encode to ascii replacing xmlcharrefs now and reopen - the original error message is:",
e,
)
except Exception as ex:
print(entry_link, entry_link.encode('ascii', errors='xmlcharrefreplace').decode('ascii'), ex )
try: if fdb_conf_entry_list_slow_downloading == 'TRUE':
web_content = response.read().decode("UTF-8")
except Exception as e:
try: try:
web_content = response.read().decode("latin-1")
print( print("trying to get slowly entry link " , entry_link)
"decoding the respone in utf8 did not work, try to decode latin1 now - the original error message is:", driver.get(entry_link)
e, time.sleep(3)
) web_content = driver.page_source
except Exception as ex:
print(ex) except Exception as e:
print("getting the html behind the entry link did not work, ori message is:", e)
else:
try:
# defining cookie to not end up in endless loop because of cookie banners pointing to redirects
url = entry_link
req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0', 'Cookie':'myCookie=oioioioi'})
response = urllib.request.urlopen(req)
print('response from first one', response)
except Exception as e:
print('cookie giving then downloading did not work, original error is:', e)
try:
response = urllib.request.urlopen(entry_link.encode('ascii', errors='xmlcharrefreplace').decode('ascii'))
print(
"opening the link did not work, try to encode to ascii replacing xmlcharrefs now and reopen - the original error message is:",
e,
)
except Exception as ex:
print(entry_link, entry_link.encode('ascii', errors='xmlcharrefreplace').decode('ascii'), ex )
try:
web_content = response.read().decode("UTF-8")
except Exception as e:
try:
web_content = response.read().decode("latin-1")
print(
"decoding the respone in utf8 did not work, try to decode latin1 now - the original error message is:",
e,
)
except Exception as ex:
print(ex)
# save interim results to files # save interim results to files
if '.pdf' in entry_link: if '.pdf' in entry_link and fdb_conf_entry_list_javascript_link == 'NONE':
file_name = "spiders/pages/" + fdb + str(i) + "/" + str(entry_id) + ".html" file_name = "spiders/pages/" + fdb + str(i) + "/" + str(entry_id) + ".html"
response = requests.get(entry_link) response = requests.get(entry_link)
@ -606,6 +640,10 @@ class fdb_spider(object):
file_name = "spiders/pages/" + fdb + str(i) + "/" + str(entry_id) + ".html" file_name = "spiders/pages/" + fdb + str(i) + "/" + str(entry_id) + ".html"
wget_wrote = False wget_wrote = False
if web_content == 'NONE': if web_content == 'NONE':
print('other downloading approaches did not work, trying requests') print('other downloading approaches did not work, trying requests')